Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1678401_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Lyudmyla Starostyuk Author-X-Name-First: Lyudmyla Author-X-Name-Last: Starostyuk Author-Name: Kay-Yut Chen Author-X-Name-First: Kay-Yut Author-X-Name-Last: Chen Author-Name: Edmund L. Prater Author-X-Name-First: Edmund L. Author-X-Name-Last: Prater Title: How ideological network influences terrorist attack tactics? An empirical study Abstract: Global news reflects the inefficiency of the current counterterrorism strategy. The number of terrorist attacks worldwide continues to grow. Multiple studies have not yet discovered how the configuration of links among terrorists drives their choice of attack. Using “the starfish and the spider” framework, this empirical study examines both the centralised and decentralised structures of the terrorist network. We draw the network from operational tactics of different ideologies. Focusing on the types of attacks, we explore similarities in terrorist operations, discern clusters among ideological movements, and draw the structure of terrorist networks over time. The findings contribute to an improved understanding of the operational conception of violent groups. It was found that almost half of ideological movements connect through clusters with several links stable over decades. These networks transformed from a centralised (spider) hierarchy to a decentralised (starfish) structure and eventually evolved into the combination of two – a hybrid organisation. Journal: Journal of Business Analytics Pages: 101-117 Issue: 2 Volume: 2 Year: 2019 Month: 7 X-DOI: 10.1080/2573234X.2019.1678401 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1678401 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:2:y:2019:i:2:p:101-117 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1693912_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Nik Rushdi Hassan Author-X-Name-First: Nik Rushdi Author-X-Name-Last: Hassan Title: The origins of business analytics and implications for the information systems field Abstract: Like many other disciplines, the information systems (IS) community has embraced big data analytics and data science. However, in the rush to exploit the popularity of this latest trend, the areas of big data analytics and data science that are most relevant to the IS field are not made clear. While many consider data analytics as an evolution of decision support systems (DSS), that is, as a technology that needs to be managed or enhanced, this essay traces the complex origins and philosophy of analytics instead back to Luhn’s text analytics in the late 1950s, Naur’s Computing as a Human Activity and his datalogy, Tukey’s Future of Data Analysis of the 1960s, and Codd’s relational database schema in the 1970s, well before big data analytics and data science became industry buzzwords. Many of what is now considered mainstream thinking in big data analytics and data science can be traced back to these visionaries. This essay examines the implications of the complex origins of data analytics and data science for the IS field, specifically on how those different discourses impact future research and practice. Journal: Journal of Business Analytics Pages: 118-133 Issue: 2 Volume: 2 Year: 2019 Month: 7 X-DOI: 10.1080/2573234X.2019.1693912 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1693912 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:2:y:2019:i:2:p:118-133 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1678400_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Yonggang Lu Author-X-Name-First: Yonggang Author-X-Name-Last: Lu Title: Bayesian assessment of predictors’ contributions to variation in the predictive performance of a logistic regression model Abstract: The logistic regression model is the algorithm most commonly applied in business analytics applications for classifying objects into binary categories among industrial users. This paper presents a Bayesian approach to assessing the contributions of predictors to the predictive performance of the classification model. Our proposed approach has two novel features that distinguish it from the usual approaches for such purpose. First, our approach ranks different predictors based on their contributions to variation in a model’s predictive performance, thus addressing the challenges of prediction risk and suggesting modelling strategy. Second, our approach can evaluate the contributions of every individual predictor each pair of two predictors. Hence, it can provide valuable information for managers on highly defined and detail-oriented business inquiries, complementary to the routine information conveyed by the usual methods for variable and feature selection purpose. We demonstrate the proposed approach using an example in credit risk management. Journal: Journal of Business Analytics Pages: 134-146 Issue: 2 Volume: 2 Year: 2019 Month: 7 X-DOI: 10.1080/2573234X.2019.1678400 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1678400 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:2:y:2019:i:2:p:134-146 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1675478_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Alon Yaakobi Author-X-Name-First: Alon Author-X-Name-Last: Yaakobi Author-Name: Moshe Goresh Author-X-Name-First: Moshe Author-X-Name-Last: Goresh Author-Name: Iris Reychav Author-X-Name-First: Iris Author-X-Name-Last: Reychav Author-Name: Roger McHaney Author-X-Name-First: Roger Author-X-Name-Last: McHaney Author-Name: Lin Zhu Author-X-Name-First: Lin Author-X-Name-Last: Zhu Author-Name: Hanoch Sapoznikov Author-X-Name-First: Hanoch Author-X-Name-Last: Sapoznikov Author-Name: Yuval Lib Author-X-Name-First: Yuval Author-X-Name-Last: Lib Title: Organisational project evaluation via machine learning techniques: an exploration Abstract: This study explores ways an organisation can save time; review all proposed innovative, internal ideas; and, identify relevant start-up companies able to bring these ideas to fruition within a knowledge management framework. It uses text-mining techniques, including Python for data extraction and manipulation and topic modelling with Latent Dirichlet Allocation and Jaccard similarity indexes as a basis for evaluation of potentially valuable project ideas. Results show that internal organisational project ideas can be automatically matched with external data regarding potential implementation partners using big data knowledge management approaches. This ensures internal ideas are not overlooked or lost, but rather considered further so potentially profitable and viable opportunities are not missed. Increased use of big data to predict innovation and add value opens new channels to utilise text analysis in organisations and ensure internal innovation through a sustainable knowledge management approach. Journal: Journal of Business Analytics Pages: 147-159 Issue: 2 Volume: 2 Year: 2019 Month: 7 X-DOI: 10.1080/2573234X.2019.1675478 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1675478 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:2:y:2019:i:2:p:147-159 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1649991_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Michael O’Neill Author-X-Name-First: Michael Author-X-Name-Last: O’Neill Author-Name: Anthony Brabazon Author-X-Name-First: Anthony Author-X-Name-Last: Brabazon Title: Business analytics capability, organisational value and competitive advantage Abstract: Business Analytics makes the assumption that given a sufficient set of analytics capabilities exist within an organisation, the existence of these capabilities will result in the generation of organisational value and/or competitive advantage. Taken further, do enhanced capability levels lead to enhanced impact for organisations? Capability in this study is grounded in the four pillars of Governance, Culture, Technology and People from the Cosic, Shanks and Maynard capability framework. We set out to undertake the first empirical investigation to measure if there is a positive relationship between Business Analytics capability levels as defined by Cosic, Shanks and Maynard, and the generation of value and competitive advantage for organisations, and do enhanced capability levels lead to enhanced impact. Data gathered from a survey of 64 senior analytics professionals from 17 sectors provides evidence to support that a strong and statistically significant correlation exists between higher capability levels and the ability to generate enhanced organisational value and competitive advantage. Additionally, a revised definition of Business Analytics is proposed, given that Business Analytics should give rise to organisational value and/or competitive advantage and that for this to occur the necessary capabilities must be in place. Journal: Journal of Business Analytics Pages: 160-173 Issue: 2 Volume: 2 Year: 2019 Month: 7 X-DOI: 10.1080/2573234X.2019.1649991 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1649991 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:2:y:2019:i:2:p:160-173 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2088412_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Veronika Plotnikova Author-X-Name-First: Veronika Author-X-Name-Last: Plotnikova Author-Name: Marlon Dumas Author-X-Name-First: Marlon Author-X-Name-Last: Dumas Author-Name: Alexander Nolte Author-X-Name-First: Alexander Author-X-Name-Last: Nolte Author-Name: Fredrik Milani Author-X-Name-First: Fredrik Author-X-Name-Last: Milani Title: Designing a data mining process for the financial services domain Abstract: The implementation of data mining projects in complex organisations requires well-defined processes. Standard data mining processes, such as CRISP-DM, have gained broad adoption over the past two decades. However, numerous studies demonstrated that organisations often do not apply CRISP-DM and related processes as-is, but rather adapt them to address industry-specific requirements. Accordingly, a number of sector-specific adaptations of standard data mining processes have been proposed. So far, however, no such adaptation has been suggested for the financial services sector. This paper addresses the gap by designing and evaluating a Financial Industry Process for Data Mining (FIN-DM). FIN-DM adapts and extends CRISP-DM to address regulatory compliance, governance, and risk management requirements inherent in the financial sector, and to embed quality assurance as an integral part of the data mining project life-cycle. The framework has been iteratively designed and validated with data mining and IT experts in a financial services organisation. Journal: Journal of Business Analytics Pages: 140-166 Issue: 2 Volume: 6 Year: 2023 Month: 04 X-DOI: 10.1080/2573234X.2022.2088412 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2088412 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:2:p:140-166 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2100834_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Gaurav Dixit Author-X-Name-First: Gaurav Author-X-Name-Last: Dixit Author-Name: Amit Kumar Kushwaha Author-X-Name-First: Amit Kumar Author-X-Name-Last: Kushwaha Title: Algorithmic enhancements to identify predictable components from users’ data and a framework to detect misinformation in social media Abstract: The flow of distorted information on social media platforms cannot always be handled. As a result, digital misinformation has become a significant social, political, and technological risk factor. Extant research on detecting misinformation in social networks has focused on using metadata or characteristics of influential actors (users) and their group dynamics in isolation, but less on the act (information content) itself and on developing an integrated approach. We unify them to produce a data science framework to detect valid instances of misinformation from social media such as Twitter. Here we develop novel and efficient algorithmic improvements to extract predictable components from users’ data. The model results demonstrate a significant increase in performance beyond typical incremental improvements. This research proposes a novel term weighting scheme, clique-based features, and a metadata-based feature. These contributions to the data science literature can be helpful for future studies in the social media context. Journal: Journal of Business Analytics Pages: 112-126 Issue: 2 Volume: 6 Year: 2023 Month: 04 X-DOI: 10.1080/2573234X.2022.2100834 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2100834 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:2:p:112-126 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2104663_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Gaurav Vijay Karkhanis Author-X-Name-First: Gaurav Vijay Author-X-Name-Last: Karkhanis Author-Name: Suresh Udhavdas Chandnani Author-X-Name-First: Suresh Udhavdas Author-X-Name-Last: Chandnani Author-Name: Swapnajit Chakraborti Author-X-Name-First: Swapnajit Author-X-Name-Last: Chakraborti Title: Analysis of employee perception of employer brand: a comparative study across business cycles using structural topic modelling Abstract: Employer branding is an important measure to attract prospective employees and to motivate, engage, and retain their current employees. Employer branding is instrumental for the employer to position the organisation in the minds of current and potential employees by using a combination of economic, psychological, and functional benefits. In the current research the authors implement a set of natural language processing techniques (structural topic modelling) on the employee reviews posted on Glassdoor.com (an online platform where the employees can post reviews about their current and previous employers). The study has thematically structured the 35,075 reviews from 8 Information Technology companies, spanning 5 years from 2015 to 2019. The study compares the employer branding parameters and has identified the prominent dimensions across the expansionary (2015–2017) and contractionary (2017–2019) phases of business cycles. A significant difference in topical proportions were found across the business cycles, suggesting different priorities for different dimensions of the employer brand during expansionary and contractionary phases. The findings would serve as guidance for HR managers to understand the trends in the employee perceptions in the context of changing macro-environment situations and accordingly recalibrate their existing strategies for talent attraction and retention Journal: Journal of Business Analytics Pages: 95-111 Issue: 2 Volume: 6 Year: 2023 Month: 04 X-DOI: 10.1080/2573234X.2022.2104663 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2104663 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:2:p:95-111 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2122880_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Hamed M Zolbanin Author-X-Name-First: Hamed M Author-X-Name-Last: Zolbanin Author-Name: Donald Wynn Author-X-Name-First: Donald Author-X-Name-Last: Wynn Title: From star rating to sentiment rating: using textual content of online reviews to develop more effective reputation systems for peer-to-peer accommodation platforms Abstract: Star ratings on P2P accommodation platforms are highly positive. Such biases have led many users to utilise selective processing strategies to evaluate the textual content of online reviews. However, when many reviews are available for a product or a service, these strategies would be suboptimal at best, posing several challenges to the users of peer-to-peer (P2P) accommodation platforms. To enable the guests to perform more informed evaluations and overcome the challenges that the skewed distribution of star ratings creates for decision-making, we employ content analysis tools to derive an aggregated sentiment score for each listing. Using this score, we define a new measure, called “sentiment rating”, that compares a listing with other similar listings based on their textual reviews. Our choice-based conjoint experiment suggests that unlike users’ initial perception about the function of star rating as the most salient factor in evaluating P2P listings, users actually attribute more importance to sentiment ratings of P2P accommodations. Therefore, a text-based summary of online reviews would indeed help users in evaluating alternatives on a P2P platform and in decision making. We argue that a text-based quantitative summary of user reviews could be a useful supplements to (or substitutes for) star ratings on P2P accommodation platforms and even online retailing websites. Journal: Journal of Business Analytics Pages: 127-139 Issue: 2 Volume: 6 Year: 2023 Month: 04 X-DOI: 10.1080/2573234X.2022.2122880 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2122880 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:2:p:127-139 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1740616_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Christian Dremel Author-X-Name-First: Christian Author-X-Name-Last: Dremel Author-Name: Emanuel Stoeckli Author-X-Name-First: Emanuel Author-X-Name-Last: Stoeckli Author-Name: Jochen Wulf Author-X-Name-First: Jochen Author-X-Name-Last: Wulf Title: Management of analytics-as-a-service - results from an action design research project Abstract: The ability to generate business-relevant information from data and to exploit it to improve business processes, decision-making, products, and services (business analytics) is a key success factor for businesses today. Answering the call for further research on success-relevant practices and instruments for managing business analytics, we report on the results of a three-year action design research (ADR) project at a global car manufacturer. Drawing on the socio-technical systems theory, we identify seven meta-requirements and specify four principles for the design of an instrument to manage Analytics-as-a-Service (AaaS) portfolios. Our results reinforce the importance of coordinating different socio-technical components in business analytics initiatives and demonstrate how concrete management instruments, such as a proposed portfolio management tool, contribute to socio-technical alignment. For practitioners, the documented design components provide guidance on how to design and implement similar instruments that support the systematic management of AaaS portfolios. Journal: Journal of Business Analytics Pages: 1-16 Issue: 1 Volume: 3 Year: 2020 Month: 01 X-DOI: 10.1080/2573234X.2020.1740616 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1740616 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:3:y:2020:i:1:p:1-16 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1768808_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Eunjung Lee Author-X-Name-First: Eunjung Author-X-Name-Last: Lee Author-Name: Huimin Zhao Author-X-Name-First: Huimin Author-X-Name-Last: Zhao Title: Deriving topic-related and interaction features to predict top attractive reviews for a specific business entity Abstract: As large volumes of online reviews are being generated, both online businesses and customers are confronted with big data challenges. Previous studies have developed various methods to predict the helpfulness of online reviews. These methods have disregarded the aspects of the business entities when dealing with datasets for prediction and evaluation and have not considered interactions between a review and the target business entity. In this paper, we propose a novel method to predict the top attractive reviews for a specific business entity. We also propose topic-related features to characterise the topics in a review and interaction features to reflect relationships between a review and the business entity it covers. Our empirical evaluation shows the utility of our proposed method and features. Journal: Journal of Business Analytics Pages: 17-31 Issue: 1 Volume: 3 Year: 2020 Month: 01 X-DOI: 10.1080/2573234X.2020.1768808 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1768808 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:3:y:2020:i:1:p:17-31 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1763862_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Theja Tulabandhula Author-X-Name-First: Theja Author-X-Name-Last: Tulabandhula Author-Name: Shailesh Vaya Author-X-Name-First: Shailesh Author-X-Name-Last: Vaya Author-Name: Aritra Dhar Author-X-Name-First: Aritra Author-X-Name-Last: Dhar Title: Privacy preserving targeted advertising and recommendations Abstract: Recommendation systems form the centerpiece of a rapidly growing trillion dollar online advertisement industry. Curating and storing profile information of users on web portals can seriously breach their privacy. Modifying such systems to achieve private recommendations without extensive redesign of the recommendation process typically requires communication of large encrypted information, making the whole process inefficient due to high latency. In this paper, we present an efficient recommendation system redesign, in which user profiles are maintained entirely on their device/web-browsers, and appropriate recommendations are fetched from web portals in an efficient privacy-preserving manner. We base this approach on precomputing compressed data structures from historical data and running low latency lookups when providing recommendations in real-time. Journal: Journal of Business Analytics Pages: 32-55 Issue: 1 Volume: 3 Year: 2020 Month: 01 X-DOI: 10.1080/2573234X.2020.1763862 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1763862 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:3:y:2020:i:1:p:32-55 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1776164_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Shylu John Author-X-Name-First: Shylu Author-X-Name-Last: John Author-Name: Bhavin J. Shah Author-X-Name-First: Bhavin J. Author-X-Name-Last: Shah Author-Name: Pradeep Kartha Author-X-Name-First: Pradeep Author-X-Name-Last: Kartha Title: Refund fraud analytics for an online retail purchases Abstract: Online shopping is growing fast across the globe and so are its complexities. Fraud is a complicated phenomenon and its mitigation is critical for running a smooth business. The case considered for the present study is fraud mitigation in return – refund process managed by the customer services of an online retail business. Predictive analytics approach was used to identify early indicators of agent refund fraud – a rare event. The technique used to solve the problem was a Penalised Likelihood based Logistic Regression model. The proposed model allowed the business to select top 5% sample of refund transactions with a higher likelihood of fraud as indicated and queue them for an audit. Implementation of this model resulted in an incremental lift in fraud capture rate. Journal: Journal of Business Analytics Pages: 56-66 Issue: 1 Volume: 3 Year: 2020 Month: 01 X-DOI: 10.1080/2573234X.2020.1776164 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1776164 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:3:y:2020:i:1:p:56-66 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1751569_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Serhat Simsek Author-X-Name-First: Serhat Author-X-Name-Last: Simsek Author-Name: Onur Genc Author-X-Name-First: Onur Author-X-Name-Last: Genc Author-Name: Abdullah Albizri Author-X-Name-First: Abdullah Author-X-Name-Last: Albizri Author-Name: Semih Dinc Author-X-Name-First: Semih Author-X-Name-Last: Dinc Author-Name: Bilal Gonen Author-X-Name-First: Bilal Author-X-Name-Last: Gonen Title: Artificial neural network incorporated decision support tool for point velocity prediction Abstract: This study aims to develop a decision support tool for identifying the point velocity profiles in rivers. The tool enables managers to make timely and accurate decisions, thereby eliminating a substantial amount of time, cost, and effort spent on measurement procedures. In the proposed study, three machine learning classification algorithms, Artificial Neural Networks (ANN), Classification & Regression Trees (C&RT) and Tree Augmented Naïve Bayes (TAN) along with Multinomial Logistic Regression (MLR), are employed to classify the point velocities in rivers. The results showed that ANN has outperformed the other classification algorithms in predicting the outcome that was converted into 10 ordinal classes, by achieving the accuracy level of 0.46. Accordingly, a decision support tool incorporating ANN has been developed. Such a tool can be utilized by end-users (managers/practitioners) without any expertise in the machine learning field. This tool also helps in achieving success for financial investors and other relevant stakeholders. Journal: Journal of Business Analytics Pages: 67-78 Issue: 1 Volume: 3 Year: 2020 Month: 01 X-DOI: 10.1080/2573234X.2020.1751569 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1751569 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:3:y:2020:i:1:p:67-78 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1838958_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Hilde Patron Author-X-Name-First: Hilde Author-X-Name-Last: Patron Author-Name: Laureano Gomez Author-X-Name-First: Laureano Author-X-Name-Last: Gomez Title: A market basket analysis of the US auto-repair industry Abstract: Market basket analysis (MBA), or the mining of transactional data to uncover association rules, is a popular methodology used in managerial decision making. MBA is centered around three key parameters: support, confidence, and lift, and the choice of starting values for these parameters can have a significant impact on the results of the analysis. We develop a procedure in R around the Apriori algorithm to help in identifying lift maximising rules when the support covers a specified proportion. The procedure facilitates the choice of minimum parameters, eliminates redundancies, and organizes the resulting association rules into actionable formats. When applied to the US auto repair data, we find un-exploited bundling packages that can be added to the scheduled maintenance services of traditional marketing campaigns. Journal: Journal of Business Analytics Pages: 79-92 Issue: 2 Volume: 3 Year: 2020 Month: 07 X-DOI: 10.1080/2573234X.2020.1838958 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1838958 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:3:y:2020:i:2:p:79-92 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1832866_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Reza Gharoie Ahangar Author-X-Name-First: Reza Author-X-Name-Last: Gharoie Ahangar Author-Name: Robert Pavur Author-X-Name-First: Robert Author-X-Name-Last: Pavur Author-Name: Mahdi Fathi Author-X-Name-First: Mahdi Author-X-Name-Last: Fathi Author-Name: Abdulazeez Shaik Author-X-Name-First: Abdulazeez Author-X-Name-Last: Shaik Title: Estimation and demographic analysis of COVID-19 infections with respect to weather factors in Europe Abstract: The main objective of this study is to investigate the relationship between the COVID-19 and the weather factors of the most populated and industrialised countries in Europe and propose the best mathematical model to forecast the daily number of COVID-19 cases. To find the relationship between the COVID-19 and the weather factors of absolute humidity and temperature in Spain, France, Italy, Germany, and the United Kingdom, we conducted a Poisson analysis. We also used the General Linear Neural Network (GRNN) model to forecast the trend and number of daily COVID-19 cases in these European countries. The results reveal a statistically significant negative relationship between the number of COVID-19 infections and weather factors of temperature & absolute humidity. Furthermore, the results show a stronger negative relationship between COVID-19 and absolute humidity than temperature. In our proposed GRNN method, we find better compatibility for the COVID-19 cases in Italy relative to the other European countries in this study. Journal: Journal of Business Analytics Pages: 93-106 Issue: 2 Volume: 3 Year: 2020 Month: 07 X-DOI: 10.1080/2573234X.2020.1832866 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1832866 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:3:y:2020:i:2:p:93-106 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1785342_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Triss Ashton Author-X-Name-First: Triss Author-X-Name-Last: Ashton Author-Name: Nicholas Evangelopoulos Author-X-Name-First: Nicholas Author-X-Name-Last: Evangelopoulos Author-Name: Audhesh Paswan Author-X-Name-First: Audhesh Author-X-Name-Last: Paswan Author-Name: Victor R. Prybutok Author-X-Name-First: Victor R. Author-X-Name-Last: Prybutok Author-Name: Robert Pavur Author-X-Name-First: Robert Author-X-Name-Last: Pavur Title: Assessing text mining algorithm outcomes Abstract: There is a surge in the development of decision-oriented analysis tools intended to extract actionable information from text. These tools integrate various text-mining methods that were performance tested in a manner that was often biased toward the new system. Those tests primarily utilised descriptive measurement criteria and test datasets that are inconsistent with most business corpora. We propose and test a user-oriented judgment approach that allows testing under controlled customer-oriented corpora and generates effect size measures.  To illustrate the approach, customer relations data was analysed by latent semantic analysis and latent Dirichlet analysis with results evaluated by prospective business analysts. Reporting includes comparisons of results with published literature. While the research centres on the context-region text-mining systems, literature comparisons include word-embedding methods. The analysis concludes that none of the systems reviewed possess a repeatable statistical advantage over the others. Instead, distribution attributes, algorithm configuration, and the evaluation task drive results. Journal: Journal of Business Analytics Pages: 107-121 Issue: 2 Volume: 3 Year: 2020 Month: 07 X-DOI: 10.1080/2573234X.2020.1785342 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1785342 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:3:y:2020:i:2:p:107-121 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1829508_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Bart Willigers Author-X-Name-First: Bart Author-X-Name-Last: Willigers Title: How advanced analytics create (Core) value: an example from a pharmaceutical company, AstraZeneca Abstract: Large investments in analytics demonstrate that the pharmaceutical industry has embraced the value proposition of data science. This excitement however does not imply that companies, currently, have a solid understanding how data science creates value. Management rely on data scientists for the value delivery of advanced analytics. Objectives of data scientists and management are not necessarily aligned. Choices made by data scientists might be suboptimal from a wholistic corporate perspective. Conversely management might lack technical expertise. This situation is an example of a principal-agent problem. AstraZeneca is making significant investments in analytical capabilities. AstraZeneca beliefs that investment decisions should not be strictly determined by monetary objectives, instead corporate Core Values should be used as guiding principles. The relationship between objectives and attributes are captured in an objective hierarchy network. This model reduces the information asymmetry between data scientists and its leaders by creating clarity regarding the objectives pursued by AstraZeneca. Journal: Journal of Business Analytics Pages: 122-137 Issue: 2 Volume: 3 Year: 2020 Month: 07 X-DOI: 10.1080/2573234X.2020.1829508 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1829508 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:3:y:2020:i:2:p:122-137 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1834883_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Anuradha Banerjee Author-X-Name-First: Anuradha Author-X-Name-Last: Banerjee Author-Name: Basav Roychoudhury Author-X-Name-First: Basav Author-X-Name-Last: Roychoudhury Author-Name: Bidyut Jyoti Gogoi Author-X-Name-First: Bidyut Jyoti Author-X-Name-Last: Gogoi Title: Determining rank in the market using a neutrosophic decision support system Abstract: A company’s rank vis-à-vis that of its competitors is an important metric in understanding its position in the market. For a company, being ranked below its competitors indicates that customers are dissatisfied with its products, signalling the need for a review of its strategies. Existing state-of-the-art methods for ascertaining a company’s rank do not utilise the valuable data available on social media or most smart technologies such as the Internet of Things (IoT) and artificial intelligence. This study develops a new method to estimate a company’s rank using company-deployed intelligent software agents and social IoT(SIoT) objects. The company objects collect real-time feedback about one or more of the company products from social networks for storage and analysis. These company objects are equipped with questionnaires with important metrics such as the Customer Happiness Index, opinion on features of competitive products, expectations in upcoming models of the product. Then neutrosophic numbers have been used to determine truthiness, falsity and indeterminacy of each opinion and based on such opinions, rank of a company is determined. Journal: Journal of Business Analytics Pages: 138-157 Issue: 2 Volume: 3 Year: 2020 Month: 07 X-DOI: 10.1080/2573234X.2020.1834883 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1834883 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:3:y:2020:i:2:p:138-157 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1760741_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Serhat Simsek Author-X-Name-First: Serhat Author-X-Name-Last: Simsek Author-Name: Mehmet Gumus Author-X-Name-First: Mehmet Author-X-Name-Last: Gumus Author-Name: Mohamed Khalafalla Author-X-Name-First: Mohamed Author-X-Name-Last: Khalafalla Author-Name: Tahir Bachar Issa Author-X-Name-First: Tahir Bachar Author-X-Name-Last: Issa Title: A hybrid data analytics approach for high-performance concrete compressive strength prediction Abstract: Contrary to the popular belief cited in the literature, the proposed data analytics technique shows that multiple linear regression (MLR) can achieve as high a predictive power as some of the black box models when the necessary interventions are implemented pertaining to the regression diagnostic. Such an MLR model can be utilised to design an optimal concrete mix, as it provides the explicit and accurate relationships between the HPC components and the expected compressive strength. Moreover, the proposed study offers a decision support tool incorporating the Extreme Gradient Boosting (XGB) model to bridge the gap between black-box models and practitioners. The tool can be used to make faster, more data-driven, and accurate managerial decisions without having any expertise in the required fields, which would reduce a substantial amount of time, cost, and effort spent on measurement procedures of the compressive strength of HPC. Journal: Journal of Business Analytics Pages: 158-168 Issue: 2 Volume: 3 Year: 2020 Month: 07 X-DOI: 10.1080/2573234X.2020.1760741 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1760741 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:3:y:2020:i:2:p:158-168 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1992305_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Kanupriya Singh Author-X-Name-First: Kanupriya Author-X-Name-Last: Singh Author-Name: Isa Jahnke Author-X-Name-First: Isa Author-X-Name-Last: Jahnke Author-Name: Abu Mosa Author-X-Name-First: Abu Author-X-Name-Last: Mosa Author-Name: Prasad Calyam Author-X-Name-First: Prasad Author-X-Name-Last: Calyam Title: The winding road of requesting healthcare data for analytics purposes: using the one-interview mental model method for improving services of health data governance and big data request processes Abstract: Medical schools store large sets of patient data. The data is important for the analysis of trends and patterns in healthcare practice. However, obtaining access to the data can be problematic due to the data protection mechanisms. In this study, we investigate the current practices from the lens of both the data requester and the data provider. Results reveal discrepancies between how the provider organises the data governance process, how the process is presented to the data requester, and the data requester’s perception of satisfactory user experience. This study provides a simple one interview mental model method approach for data governance services to reveal potential problems in the process. This is a quick and effective method for data providers to help uncover the challenges and to provide foundations for future fully automated (human out of the loop) systems for data accessibility in healthcare organisations. Journal: Journal of Business Analytics Pages: 1-18 Issue: 1 Volume: 6 Year: 2023 Month: 01 X-DOI: 10.1080/2573234X.2021.1992305 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1992305 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:1:p:1-18 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1999179_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Osman Aydas Author-X-Name-First: Osman Author-X-Name-Last: Aydas Author-Name: Anthony Ross Author-X-Name-First: Anthony Author-X-Name-Last: Ross Author-Name: Hamieda Parker Author-X-Name-First: Hamieda Author-X-Name-Last: Parker Author-Name: Sepideh Alavi Author-X-Name-First: Sepideh Author-X-Name-Last: Alavi Title: Using efficiency frontiers to visualise suppliers’ performance capabilities: moving beyond supplier rationalisation Abstract: This paper offers a framework for analysis to benefit buying firms as they evaluate current and prospective suppliers, and to assist supplying organisations in becoming more competitive. It explores the notion of performance improvement frontiers for suppliers, in the context of developing suppliers rather than rationalising or pruning them. Dual-efficiency (strengths and weaknesses) frontiers are constructed using inverted efficiency techniques. Unilateral and bilateral approaches to the construction of these frontiers are examined. It is found that certain information content of bilaterally determined DEA assurance ranges can serve as a compromise between the buyer’s ideal performance priorities and a supplier’s capability-based priorities. For this reason, it represents a reasonable and jointly determined set of performance expectations for buyers to recommend to the supplier set. For the suppliers themselves, the bilateral ranges contribute a prioritised behavioural focus to develop or improve their capabilities on specific performance attributes. Journal: Journal of Business Analytics Pages: 19-38 Issue: 1 Volume: 6 Year: 2023 Month: 01 X-DOI: 10.1080/2573234X.2021.1999179 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1999179 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:1:p:19-38 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2064777_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Xingxing Zu Author-X-Name-First: Xingxing Author-X-Name-Last: Zu Author-Name: Xiaoyin Wang Author-X-Name-First: Xiaoyin Author-X-Name-Last: Wang Author-Name: Yunwei Cui Author-X-Name-First: Yunwei Author-X-Name-Last: Cui Title: Forecasting natural gas consumption in residential and commercial sectors in the US Abstract: The paper proposes a parallel forecasting approach for weekly natural gas consumption in the US residential and commercial sectors, which models scrape data and ratio data separately and then combines the outputs to generate the forecasts. To improve forecasting accuracy, both semi-parametric and nonparametric models, including dynamic linear regression model and dynamic semi-parametric model, are adopted to model the effects of weather variables, and time series techniques are employed to address the serial correlation exhibited by the data. An algorithm focusing on forecasting accuracy is proposed to select the smoothing parameter for serially correlated data. The proposed model is empirically tested using data in the New England area from 2013 to 2018 and benchmarked against some deep learning approaches including Deep Neural Network, Long Short-Term Memory Neural Network, and Gated Recurrent Unit Neural Network methods. Overall, the results show that the proposed approach performs well in generating accurate forecasts. Journal: Journal of Business Analytics Pages: 77-94 Issue: 1 Volume: 6 Year: 2023 Month: 01 X-DOI: 10.1080/2573234X.2022.2064777 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2064777 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:1:p:77-94 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2041370_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Subrat Sarangi Author-X-Name-First: Subrat Author-X-Name-Last: Sarangi Author-Name: RK Renin Singh Author-X-Name-First: RK Renin Author-X-Name-Last: Singh Title: Winning one-day international cricket matches: a cross-team perspective Abstract: The study analyses the predictors of a win for four international cricket teams in the one-day international cricket format. A binary logistic regression is used to determine the relationship between the independent variables, i.e., fours and sixes scored, bowling economy, extras conceded, fielding dismissals, the number of debutants from each side, umpire’s nationality, pitch condition, and season of play vis-à-vis odds of a win. The study found that the number of fielding dismissals and bowler economy significantly influence the odds of winning for all four teams. Further, the nationality of the umpire did not affect any team, while other variables influenced the fortunes of different teams differently. Proposed models in the paper can be used by team management and coaches in devising match strategy and player selection for higher win outcomes based on a combination of historical trend data for specific variables and actual data for the others. Journal: Journal of Business Analytics Pages: 39-58 Issue: 1 Volume: 6 Year: 2023 Month: 01 X-DOI: 10.1080/2573234X.2022.2041370 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2041370 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:1:p:39-58 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2046514_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Salih Tutun Author-X-Name-First: Salih Author-X-Name-Last: Tutun Author-Name: Ali Tosyali Author-X-Name-First: Ali Author-X-Name-Last: Tosyali Author-Name: Hossein Sangrody Author-X-Name-First: Hossein Author-X-Name-Last: Sangrody Author-Name: Mohammad Khasawneh Author-X-Name-First: Mohammad Author-X-Name-Last: Khasawneh Author-Name: Marina Johnson Author-X-Name-First: Marina Author-X-Name-Last: Johnson Author-Name: Abdullah Albizri Author-X-Name-First: Abdullah Author-X-Name-Last: Albizri Author-Name: Antoine Harfouche Author-X-Name-First: Antoine Author-X-Name-Last: Harfouche Title: Artificial intelligence in energy industry: forecasting electricity consumption through cohort intelligence & adaptive neural fuzzy inference system Abstract: Demand forecasting is critical for energy systems, as energy is difficult to store and should only be supplied as needed. Researchers attempted to improve forecasts of energy consumption. However, they assume independent factors increase at a constant growth rate, which is unrealistic. Existing methods are designed to determine annual consumption, whereas energy-planning organizations rely on short- or medium-term consumption values. Therefore, we propose a new forecasting framework that introduces new models and scenarios. We apply a cohort intelligence-based adaptive neuro-fuzzy inference system (CI-ANFIS) with a subtractive clustering and grid partition approach to forecast net electricity consumption. One challenge in accurately predicting electricity consumption for specific projection intervals is missing values for factors independent of those known for existing net consumption. Then, we utilize a regression equation scenario approach. We test our framework using a real-world energy consumption dataset and show that our proposed framework outperforms the existing methods. Journal: Journal of Business Analytics Pages: 59-76 Issue: 1 Volume: 6 Year: 2023 Month: 01 X-DOI: 10.1080/2573234X.2022.2046514 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2046514 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:1:p:59-76 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1645574_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Mahsa Ashouri Author-X-Name-First: Mahsa Author-X-Name-Last: Ashouri Author-Name: Galit Shmueli Author-X-Name-First: Galit Author-X-Name-Last: Shmueli Author-Name: Chor-Yiu Sin Author-X-Name-First: Chor-Yiu Author-X-Name-Last: Sin Title: Tree-based methods for clustering time series using domain-relevant attributes Abstract: We propose two methods for time-series clustering that capture temporal information (trend, seasonality, autocorrelation) and domain-relevant cross-sectional attributes. The methods are based on model-based partitioning (MOB) trees and can be used as automated yet transparent tools for clustering large collections of time series. We address the challenge of using common time-series models in MOB by instead utilising least squares regression. We propose two methods. The single-step method clusters series using trend, seasonality, lags and domain-relevant cross-sectional attributes. The two-step method first clusters by trend, seasonality and cross-sectional attributes, and then clusters the residuals by autocorrelation and domain-relevant attributes. Both methods produce clusters interpretable by domain experts. We illustrate our approach by considering one-step-ahead forecasting and compare to autoregressive integrated moving average (ARIMA) models for forecasting many Wikipedia pageviews time series. The tree-based approach produces forecasts on par with ARIMA, yet is significantly faster and more efficient, thereby suitable for large collections of time-series. The simple parametric forecasting models allow for interpretable time-series clusters. Journal: Journal of Business Analytics Pages: 1-23 Issue: 1 Volume: 2 Year: 2019 Month: 1 X-DOI: 10.1080/2573234X.2019.1645574 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1645574 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:2:y:2019:i:1:p:1-23 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1645575_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Gauthier Lanot Author-X-Name-First: Gauthier Author-X-Name-Last: Lanot Author-Name: Mattias Vesterberg Author-X-Name-First: Mattias Author-X-Name-Last: Vesterberg Title: An empirical model of the decision to switch between electricity price contracts Abstract: In this paper, we explore how sensitive the timing of switches between electricity contracts is to current and past prices. We present a model for time series of individual binary decisions which depends on the history of past and present prices. The model is based on the Bayesian learning procedure which is at the core of sequential decision-making. Given a-priori distributions of the information conditional on the state of the world, we show that the model captures dependence on past prices in a straightforward fashion. We estimate by maximum likelihood the parameters of the model on a sample of Swedish households who decide over time between competing electricity price contracts. The estimated parameters suggest that households do respond to prices by switching between contracts and that the response to price can be sizeable for alternative price processes. Importantly, the model structure implies that in general, the response to a price change will not be immediate but delayed. Journal: Journal of Business Analytics Pages: 24-46 Issue: 1 Volume: 2 Year: 2019 Month: 1 X-DOI: 10.1080/2573234X.2019.1645575 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1645575 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:2:y:2019:i:1:p:24-46 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1609341_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Kevin P. Scheibe Author-X-Name-First: Kevin P. Author-X-Name-Last: Scheibe Author-Name: Sree Nilakanta Author-X-Name-First: Sree Author-X-Name-Last: Nilakanta Author-Name: Cliff T. Ragsdale Author-X-Name-First: Cliff T. Author-X-Name-Last: Ragsdale Author-Name: Bob Younie Author-X-Name-First: Bob Author-X-Name-Last: Younie Title: An evidence-based management framework for business analytics Abstract: It is said that knowledge is power, yet often, decision makers ignore information that ought to be considered. The phenomenon known as Semmelweis reflex occurs when new knowledge is rejected because it contradicts established norms. The goal of evidence-based management (EBMgt) is to help overcome Semmelweis reflex by integrating evaluated external evidence with stakeholder preference, practitioner experiences, and context. This evaluated external evidence is the product of scientific research. In this paper, we demonstrate an EBMgt business analytics model that uses computer simulation to provide scientific evidence to help decision makers evaluate equipment replacement problems, specifically the parallel machine replacement problem. The business analytics application is demonstrated in the form of a fleet management problem for a state transportation agency. The resulting analysis uses real-world data allowing decision makers to unfreeze their current system, move to a new state, and re-freeze a new system. Journal: Journal of Business Analytics Pages: 47-62 Issue: 1 Volume: 2 Year: 2019 Month: 1 X-DOI: 10.1080/2573234X.2019.1609341 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1609341 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:2:y:2019:i:1:p:47-62 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1625730_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Varol Onur Kayhan Author-X-Name-First: Varol Onur Author-X-Name-Last: Kayhan Author-Name: Alison Watkins Author-X-Name-First: Alison Author-X-Name-Last: Watkins Title: Predicting the point spread in professional basketball in real time: a data snapshot approach Abstract: Predicting the point spread of a professional basketball game is difficult but important for many stakeholders. We propose a new approach to predict the point spread in real time using in-game data. The approach uses a snapshot from the current game to identify historical games that have the same snapshot. After identifying these games, we predict the point spread of the current game using information obtained from the historical games. Using data obtained from six seasons of professional basketball games, we compare the prediction error of this approach to that of a deep learning technique, a long short-term memory network, and a general linear model. The proposed approach performs nearly the same as both models without the need for resource-intensive training. We discuss the robustness of this approach for making real-time predictions as games are underway. The findings have real-world implications for game enthusiasts, coaching staffs, and, most importantly, bettors. Journal: Journal of Business Analytics Pages: 63-73 Issue: 1 Volume: 2 Year: 2019 Month: 1 X-DOI: 10.1080/2573234X.2019.1625730 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1625730 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:2:y:2019:i:1:p:63-73 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1633890_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: John Steven Edwards Author-X-Name-First: John Steven Author-X-Name-Last: Edwards Author-Name: Eduardo Rodriguez Author-X-Name-First: Eduardo Author-X-Name-Last: Rodriguez Title: Remedies against bias in analytics systems Abstract: Advances in IT offer the possibility to develop ever more complex predictive and prescriptive systems based on analytics. Organizations are beginning to rely on the outputs from these systems without inspecting them, especially if they are embedded in the organization’s operational systems. This reliance could be misplaced unethical or even illegal if the systems contain bias. Data, algorithms and machine learning methods are all potentially subject to bias. In this article we explain the ways in which bias might arise in analytics systems, present some examples, and give some suggestions as to how to prevent or reduce it. We use a framework inspired by the work of Hammond, Keeney and Raiffa on psychological traps in human decision-making. Each of these traps “translates” into a potential type of bias for an analytics-based system. Fortunately, this means that remedies to reduce bias in human decision-making also translate into potential remedies for algorithmic systems. Journal: Journal of Business Analytics Pages: 74-87 Issue: 1 Volume: 2 Year: 2019 Month: 1 X-DOI: 10.1080/2573234X.2019.1633890 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1633890 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:2:y:2019:i:1:p:74-87 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1638735_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Charles R. Hadlock Author-X-Name-First: Charles R. Author-X-Name-Last: Hadlock Author-Name: Samuel W. Woolford Author-X-Name-First: Samuel W. Author-X-Name-Last: Woolford Title: Optimizing management of emergency gas leaks: a case study in business analytics Abstract: Managing the response to reported gas leaks is of significant importance to both utilities and regulators. This paper utilizes a business analytics approach to investigate strategies for managing gas leak response while balancing the objectives of both utilities and regulators. The approach integrates the translation of the business issue into a quantitative framework by which actual gas leak data can be analysed and modelled to measure the performance of different gas leak response strategies. An agent-based simulation model is utilized to provide a decision support platform that translates the analytic results into a visualization tool to assist stakeholders and decision makers in evaluating the impact of different response strategies. The paper highlights both the analytic methods and the related “soft skills” that must be managed in the business analytics context to ensure an outcome that is acceptable for all stakeholders. Journal: Journal of Business Analytics Pages: 88-99 Issue: 1 Volume: 2 Year: 2019 Month: 1 X-DOI: 10.1080/2573234X.2019.1638735 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1638735 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:2:y:2019:i:1:p:88-99 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1543535_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Thomas H. Davenport Author-X-Name-First: Thomas H. Author-X-Name-Last: Davenport Title: From analytics to artificial intelligence Abstract: Analytics have been employed by companies for several decades, but now many firms are interested in building their capabilities for artificial intelligence (AI). Many AI systems, however, are based on statistics and other forms of analytics. Companies can get a “running start” on AI by building upon their analytical competencies. The focus of this article is how to transition from analytics to AI. Three eras of analytical focus are detailed, with AI portrayed as a fourth era. The types of AI methods that are and are not based on analytics are described. AI applications that build on analytical strengths are discussed. Approaches to assessing analytical capabilities that relate to AI, and the development of an organizational plan and strategy for AI, are also described in brief. Journal: Journal of Business Analytics Pages: 73-80 Issue: 2 Volume: 1 Year: 2018 Month: 7 X-DOI: 10.1080/2573234X.2018.1543535 File-URL: http://hdl.handle.net/10.1080/2573234X.2018.1543535 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:1:y:2018:i:2:p:73-80 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1557020_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Vincent Whitelock Author-X-Name-First: Vincent Author-X-Name-Last: Whitelock Title: Business analytics and firm performance: role of structured financial statement data Abstract: Although business analytics has received its fair share of attention, extant research has paid insufficient attention to establishing and communicating a general understanding of the relationship between analytics and performance. In order to reduce the identified knowledge gap, this study proposes a comprehensive, theoretical framework to explain the key types of business analytics, their relationships, and how business analytics use impacts operational and financial performance. This study proposes a combination of critical systems, “holistic thinking/big picture/decision-making,” approaches to moderate key relationships to impact performance. Additionally, this study presents a case illustration of a real-world contract manufacturer, employing the proposed framework, to demonstrate the innovative use of integrated business analytics to turnaround an organization, and position it to survive, thrive, innovate, and grow. Findings indicate that firms, “overwhelmed by” and “struggling to use” data to improve business results, have a viable cost-effective framework to advance business analytics capability, in their organizations. Journal: Journal of Business Analytics Pages: 81-92 Issue: 2 Volume: 1 Year: 2018 Month: 7 X-DOI: 10.1080/2573234X.2018.1557020 File-URL: http://hdl.handle.net/10.1080/2573234X.2018.1557020 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:1:y:2018:i:2:p:81-92 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1590131_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Andra-Selina Pietsch Author-X-Name-First: Andra-Selina Author-X-Name-Last: Pietsch Author-Name: Stefan Lessmann Author-X-Name-First: Stefan Author-X-Name-Last: Lessmann Title: Topic modeling for analyzing open-ended survey responses Abstract: Open-ended responses are widely used in market research studies. Processing of such responses requires labour-intensive human coding. This paper focuses on unsupervised topic models and tests their ability to automate the analysis of open-ended responses. Since state-of-the-art topic models struggle with the shortness of open-ended responses, the paper considers three novel short text topic models: Latent Feature Latent Dirichlet Allocation, Biterm Topic Model and Word Network Topic Model. The models are fitted and evaluated on a set of real-world open-ended responses provided by a market research company. Multiple components such as topic coherence and document classification are quantitatively and qualitatively evaluated to appraise whether topic models can replace human coding. The results suggest that topic models are a viable alternative for open-ended response coding. However, their usefulness is limited when a correct one-to-one mapping of responses and topics or the exact topic distribution is needed. Journal: Journal of Business Analytics Pages: 93-116 Issue: 2 Volume: 1 Year: 2018 Month: 7 X-DOI: 10.1080/2573234X.2019.1590131 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1590131 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:1:y:2018:i:2:p:93-116 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1602002_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Amir Hassan Zadeh Author-X-Name-First: Amir Author-X-Name-Last: Hassan Zadeh Author-Name: Anand Jeyaraj Author-X-Name-First: Anand Author-X-Name-Last: Jeyaraj Title: Alignment of business and social media strategies: insights from a text mining analysis Abstract: Organisations utilise social media technologies for various customer engagement and external-facing activities in recent years. This research examines the extent to which the business strategies and social media strategies of organisations are aligned. Using a sample of 33 organisations competing in the information technology industry, the business strategies were operationalised using data extracted from the annual 10-K reports while the social media strategies were identified from the Twitter feeds. Topic modelling with latent semantic analysis revealed six different orientations in the business and social media strategies of organisations, which were used to evaluate alignment. This study also identified clusters of organisations with varying levels of alignment. Implications for research and practice are discussed. Journal: Journal of Business Analytics Pages: 117-134 Issue: 2 Volume: 1 Year: 2018 Month: 7 X-DOI: 10.1080/2573234X.2019.1602002 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1602002 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:1:y:2018:i:2:p:117-134 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1605312_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: A. E. Rodriguez Author-X-Name-First: A. E. Author-X-Name-Last: Rodriguez Author-Name: Ahmet S. Ozkul Author-X-Name-First: Ahmet S. Author-X-Name-Last: Ozkul Author-Name: Brian A. Marks Author-X-Name-First: Brian A. Author-X-Name-Last: Marks Title: Explaining impact of predictors in rankings: an illustrative case of states rankings Abstract: This study presents an approach that can be used to identify important predictors used incalculating performance rankings and gauge their sensitivities. Random Forests is a powerful machine learning tool well known for their predictive powers. It is especially suited to broach the small-n, large-p problem usually found in rankings procedures. However, random forests are unable to shed any insight intohow the examined predictors affect individual entries in the ranked set. A procedure calledLocal Interpretable Model-Agnostic Explanations (LIME) enables decision-makers to discernthe most important individual variables and their relative contributions to the outcome ofeach element in the ranked set. To explain this procedure, we use the 2016 edition of theALEC-Laffer State Rankings data. With the method proposed in this study, a state’s policymakerswould have specific knowledge on how to improve their state’s ranking. This method is ofgeneral applicability to any policy domain. Journal: Journal of Business Analytics Pages: 135-143 Issue: 2 Volume: 1 Year: 2018 Month: 7 X-DOI: 10.1080/2573234X.2019.1605312 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1605312 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:1:y:2018:i:2:p:135-143 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1873078_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Ebrahim Mortaz Author-X-Name-First: Ebrahim Author-X-Name-Last: Mortaz Author-Name: Ali Dag Author-X-Name-First: Ali Author-X-Name-Last: Dag Author-Name: Lorraine Hutzler Author-X-Name-First: Lorraine Author-X-Name-Last: Hutzler Author-Name: Christopher Gharibo Author-X-Name-First: Christopher Author-X-Name-Last: Gharibo Author-Name: Lisa Anzisi Author-X-Name-First: Lisa Author-X-Name-Last: Anzisi Author-Name: Joseph Bosco Author-X-Name-First: Joseph Author-X-Name-Last: Bosco Title: Short-term prediction of opioid prescribing patterns for orthopaedic surgical procedures: a machine learning framework Abstract: Overprescribing of opioids after surgical procedures can increase the risk of addiction in patients, and under prescribing can lead to poor quality of care. In this study, we propose a machine learning-based predictive framework to identify the varying effects of factors that are related to the opioid prescription amount after orthopaedic surgery. To predict the prescription classes, we train multiple classifiers combined with random and SMOTE over-sampling and weight-balancing techniques to cope with the imbalance state of the dataset. Our results show that the gradient boosting machines (XGB) with SMOTE achieve the highest classification accuracy. Our proposed analytical framework can be employed to assist and therefore, enable the surgeons to determine the timely changing effects of these variables. Journal: Journal of Business Analytics Pages: 1-13 Issue: 1 Volume: 4 Year: 2021 Month: 01 X-DOI: 10.1080/2573234X.2021.1873078 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1873078 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:1:p:1-13 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1863749_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Shylu John Author-X-Name-First: Shylu Author-X-Name-Last: John Author-Name: Bhavin Shah Author-X-Name-First: Bhavin Author-X-Name-Last: Shah Author-Name: Varun Dixit Author-X-Name-First: Varun Author-X-Name-Last: Dixit Author-Name: Amol Wani Author-X-Name-First: Amol Author-X-Name-Last: Wani Title: An integrated approach to renew software contract using machine learning. Abstract: Contract renewal is critical to maintaining a company’s recurring revenue source. Therefore, there is a significant emphasis on setting up an efficient process for renewal. In this study, a machine learning technique was followed to improve contract renewal rates. In addition to this, key factors affecting renewal rates were also studied in detail. The solution presented in this study used an unsupervised machine learning technique to segment high-risk resellers with relatively lower probability of renewal, which was further actioned upon by a proactive contact strategy soliciting a contract renewal. This solution was tested and monitored for a period of three quarters. It resulted in an incremental improvement in the renewal rate for the company. As part of the implementation, a user interface application was also developed, which enabled the sales specialist to list and contact high-risk (or underperformer) resellers quarter-on-quarter. Journal: Journal of Business Analytics Pages: 14-25 Issue: 1 Volume: 4 Year: 2021 Month: 01 X-DOI: 10.1080/2573234X.2020.1863749 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1863749 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:1:p:14-25 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1895681_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Mohammad Al-Ramahi Author-X-Name-First: Mohammad Author-X-Name-Last: Al-Ramahi Author-Name: Izzat Alsmadi Author-X-Name-First: Izzat Author-X-Name-Last: Alsmadi Title: Classifying insincere questions on Question Answering (QA) websites: meta-textual features and word embedding Abstract: The power of information and information exchange defines the current Internet and Online Social Networks (OSNs). With such power and influence, individuals and entities expose those networks to different types of false information. This paper proposes several classification models based on Quora insincere questions; a dataset released by Kaggle. We evaluated several models including word embeddings based on meta and word-level features. Best results were achieved using the BERT transformer with an overall accuracy of more than 95% on several individual classifiers. Overall, results indicated that the meta-textual features are important predictors for whether a question is sincere or not. In one implication, we noticed that users are putting more cognitive efforts into writing more readable sincere questions compared to insincere questions. Moreover, a dictionary is assembled from several explicit dictionaries and significant words selected from Quora questions. The dictionary showed a good performance in predicting insincere questions. Journal: Journal of Business Analytics Pages: 55-66 Issue: 1 Volume: 4 Year: 2021 Month: 01 X-DOI: 10.1080/2573234X.2021.1895681 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1895681 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:1:p:55-66 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1854625_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Duan C. J. (Chaojie) Author-X-Name-First: Duan C. J. Author-X-Name-Last: (Chaojie) Author-Name: Ananyo Chakravarty Author-X-Name-First: Ananyo Author-X-Name-Last: Chakravarty Title: Team Contingent or Sport Native? A Bayesian Analysis of Home Field Advantage in Professional Soccer Abstract: Besides confirming the existence of home advantage (HA) in professional sports competition, this work intends to breakdown HA into sub-components and trace the specific sources of HA. Using scoring performance data from ESPN FC, we fit a Bayesian multilevel-nested model to the parameters in our proposed hierarchical model of HA, allowing information obtained from the season level to inform the inferences about scoring capabilities at the upper team, league, and sport levels. Our analysis reveals that much of HA is attributed to the nature of the sport of interest as well as teams playing the sport. The results seem to endorse the view that home advantage is mainly characteristic of the sport and participating teams, while league grouping can be safely ignored as a credible contributing source. Finally, we discuss the implications of our proposed two-source model of HA for future research at the inter-sport level. Journal: Journal of Business Analytics Pages: 67-75 Issue: 1 Volume: 4 Year: 2021 Month: 01 X-DOI: 10.1080/2573234X.2020.1854625 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1854625 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:1:p:67-75 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1873077_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Philip Maymin Author-X-Name-First: Philip Author-X-Name-Last: Maymin Title: Using Scouting Reports Text To Predict NCAA → NBA Performance Abstract: Draft decisions by National Basketball Association (NBA) teams are notoriously poor. Analytics can help but are often dismissed for being too overfit, complex, risky, and incomplete. To address these concerns, we train separate leave-one-out random forests machine learning models for each collegiate NBA prospect from 2006 through 2019 with a conservative utility function on a novel comprehensive dataset including the raw text of scouting reports, combine measurements, on-court stats, mock draft placements, and more. Despite being unable to draft high school or international players, the resulting model outperforms the actual decisions of all but one NBA team, with an average gain of $100 million. Target shuffling shows that the model does not overfit and feature shuffling shows that handedness and ESPN mock draft rating, but not other mock drafts, are most important. NBA teams may be missing value by not following a disciplined, model-driven, prescriptive analytics approach to decision making. Journal: Journal of Business Analytics Pages: 40-54 Issue: 1 Volume: 4 Year: 2021 Month: 01 X-DOI: 10.1080/2573234X.2021.1873077 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1873077 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:1:p:40-54 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1863750_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Anand Jeyaraj Author-X-Name-First: Anand Author-X-Name-Last: Jeyaraj Author-Name: Amir Zadeh Author-X-Name-First: Amir Author-X-Name-Last: Zadeh Author-Name: Vikram Sethi Author-X-Name-First: Vikram Author-X-Name-Last: Sethi Title: Cybersecurity Threats and Organisational Response: Textual Analysis and Panel Regression Abstract: This study examines the relationship between cybersecurity threats faced and cybersecurity response planned by organisations. Classifying cybersecurity threats into four types – physical threats, personnel threats, communication and data threats, and operational threats – this study examines organisational responses to such threats. Using textual data on cybersecurity threats and response gathered from the 10-K reports published by 87 organisations, topic modelling was conducted to assess the threats and response. A cross-sectional time-series regression model fitted on the topic weights showed that cybersecurity response was influenced by cybersecurity threats, beyond the time-invariant control and period variables. Specifically, physical threats and operational threats influenced the technical response; physical threats, communication and data threats, and operational threats influenced the non-technical response; and personnel threats influenced the overall response. Implications for research and practice are discussed. Journal: Journal of Business Analytics Pages: 26-39 Issue: 1 Volume: 4 Year: 2021 Month: 01 X-DOI: 10.1080/2573234X.2020.1863750 File-URL: http://hdl.handle.net/10.1080/2573234X.2020.1863750 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:1:p:26-39 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1979901_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Abu Saleh Mohammad Mosa Author-X-Name-First: Abu Saleh Mohammad Author-X-Name-Last: Mosa Author-Name: Chalermpon Thongmotai Author-X-Name-First: Chalermpon Author-X-Name-Last: Thongmotai Author-Name: Humayera Islam Author-X-Name-First: Humayera Author-X-Name-Last: Islam Author-Name: Tanmoy Paul Author-X-Name-First: Tanmoy Author-X-Name-Last: Paul Author-Name: K. S. M. Tozammel Hossain Author-X-Name-First: K. S. M. Tozammel Author-X-Name-Last: Hossain Author-Name: Vasanthi Mandhadi Author-X-Name-First: Vasanthi Author-X-Name-Last: Mandhadi Title: Evaluation of machine learning applications using real-world EHR data for predicting diabetes-related long-term complications Abstract: The biggest concern about diabetes-related complications is that they are unrecognised in the early stages but can be immutable and devastating with time. Identifying the population at high risk of developing such complications can help intervene in preventative care at an early stage. This study aims to present a data-driven approach to predict the patients at higher risk for diabetes-related complications using real-world data. We used comorbid diagnostic features from the electronic health records called “Cerner Health Facts EMR Data” to build machine learning-based prediction models for three diabetes-related long-term complications: (a) eye diseases, (b) kidney diseases, and (c) neuropathy. Our developed pipeline was able to generate highly accurate models for predictions. We deduced from the F1-scores that applying the class balancing techniques improved the overall performance of the models, and SVM with oversampling technique was the most consistent classifier for all three cohorts. Journal: Journal of Business Analytics Pages: 141-151 Issue: 2 Volume: 5 Year: 2022 Month: 07 X-DOI: 10.1080/2573234X.2021.1979901 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1979901 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:5:y:2022:i:2:p:141-151 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2007803_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Amitava Mitra Author-X-Name-First: Amitava Author-X-Name-Last: Mitra Author-Name: Pankush Kalgotra Author-X-Name-First: Pankush Author-X-Name-Last: Kalgotra Title: Optimal trimming proportion in regression analysis for non-normal distributions Abstract: Regression analysis is a widely used modelling tool in business decision making. However, proper application of this methodology requires that certain assumptions, associated with the model, be satisfied. The assumption we focus on is the normality of the response variable, which is directly related to the assumption of normality of the error component. In a variety of fields in business, such as finance, marketing, information systems, operations, and healthcare, the selected dependent variable does not inherently have a normal distribution. In the regression context, where the model parameters and independent variables are assumed to be constant, the distribution of the random error component thus influences the distribution of the dependent variable. Here, we study the impact of symmetric and asymmetric error distributions on the performance of the estimated model parameters. To create robust estimates, through a process of trimming the response variable, we study the effectiveness of the trimmed estimators with respect to the ordinary least squares estimator (OLS) via a simulation procedure. Accordingly, to minimise the ratio of the mean squared error of the trimmed estimator to that of the OLS, a recommendation is developed for the optimal trimming proportion. Journal: Journal of Business Analytics Pages: 152-163 Issue: 2 Volume: 5 Year: 2022 Month: 07 X-DOI: 10.1080/2573234X.2021.2007803 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.2007803 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:5:y:2022:i:2:p:152-163 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2088411_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Arindam Ray Author-X-Name-First: Arindam Author-X-Name-Last: Ray Author-Name: Wolfgang Jank Author-X-Name-First: Wolfgang Author-X-Name-Last: Jank Author-Name: Kaushik Dutta Author-X-Name-First: Kaushik Author-X-Name-Last: Dutta Title: Impact of mobility based network on COVID-19 spread Abstract: COVID-19 has had a strong impact on this world. With the spreading of the virus and the implementation of various mitigation measures, the pandemic has indubitably upended our way of living. Research indicates that mobility is one of the key reasons of the spread. The purpose of this paper is to provide a suitable mobility measure based on intra-county and inter-county movements on the spreading of COVID-19 in the United States. Deviating from the extant research, which measures mobility by the average distance people travel, we operationalise mobility by the number of trips made. We further weigh them based on the current caseload, as the spread will not only depend on how many people are moving but also the proportion of infectious people within them. We also distinguish such trips based on their origin and destination, as that may help in taking appropriate policy decisions for intervention. Journal: Journal of Business Analytics Pages: 179-187 Issue: 2 Volume: 5 Year: 2022 Month: 07 X-DOI: 10.1080/2573234X.2022.2088411 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2088411 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:5:y:2022:i:2:p:179-187 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2103040_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Yuan Xu Author-X-Name-First: Yuan Author-X-Name-Last: Xu Author-Name: Yong Shin Park Author-X-Name-First: Yong Shin Author-X-Name-Last: Park Author-Name: Omid Jadidi Author-X-Name-First: Omid Author-X-Name-Last: Jadidi Author-Name: John Loucks Author-X-Name-First: John Author-X-Name-Last: Loucks Author-Name: Joseph Szmerekovsky Author-X-Name-First: Joseph Author-X-Name-Last: Szmerekovsky Title: Multi-objective programming for designing sustainable biogas supply chain: a case study in North Dakota, USA Abstract: This study considers the environmental and social impacts of an animal waste sourced biogas supply chain, along with economic factors for making tactical and strategic decisions. A multi-objective optimisation model is introduced to determine: 1) the best locations and capacities of biogas plants to treat cattle manure from dairy farms, and 2) the best transportation assignments from each farm to a subset of the opened biogas plants. This study formulates three objectives that include minimising total supply chain cost, carbon emissions, and social rejection. An augmented ε-constraint method is employed as a solution approach to solve the multi-objective problem. The results indicate the implementation of the proposed optimisation model has the potential to provide significant economic, environmental, and social benefits. In addition, the study finds that the allowed maximum transport distance contributes to the number and size of biogas plants used. Journal: Journal of Business Analytics Pages: 188-200 Issue: 2 Volume: 5 Year: 2022 Month: 07 X-DOI: 10.1080/2573234X.2022.2103040 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2103040 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:5:y:2022:i:2:p:188-200 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2015252_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: S. E. Hill Author-X-Name-First: S. E. Author-X-Name-Last: Hill Title: In-game win probability models for Canadian football Abstract: This article presents in-game win probability models for Canadian football. Play-by-play and wagering data for games from the Canadian Football League for the 2015 to 2019 seasons is used to create logistic regression and gradient boosting models. Models with and without the effect of pregame spread and total (over/under) data are presented and discussed. The resulting win probability models are well-calibrated and can be used to support in-game decision-making, review coaching decisions, estimate the magnitude of team “comebacks”, and potentially identify in-game wagering opportunities. An R Shiny application is provided to allow for estimation of in-game win probability for user-provided game state inputs. Opportunities for future work are identified and described. Journal: Journal of Business Analytics Pages: 164-178 Issue: 2 Volume: 5 Year: 2022 Month: 07 X-DOI: 10.1080/2573234X.2021.2015252 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.2015252 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:5:y:2022:i:2:p:164-178 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1955021_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Jeroen Baijens Author-X-Name-First: Jeroen Author-X-Name-Last: Baijens Author-Name: Tim Huygh Author-X-Name-First: Tim Author-X-Name-Last: Huygh Author-Name: Remko Helms Author-X-Name-First: Remko Author-X-Name-Last: Helms Title: Establishing and theorising data analytics governance: a descriptive framework and a VSM-based view Abstract: The rise of big data has led to many new opportunities for organisations to create value from data. However, an increasing dependence on data also poses many challenges for organisations. To overcome these challenges, organisations have to establish data analytics governance. Leading IT and information governance literature shows that governance can be implemented through mechanisms. The data analytics literature is not very abundant in describing specific governance mechanisms. Hence, there is a need to identify and describe specific data analytics governance mechanisms. To this end, a preliminary framework based on literature  was developed and validated using a multiple case study design. This resulted in an extended descriptive framework that can aide managers in implementing data analytics governance. Furthermore, we draw on viable system model (VSM) theory to make a theoretical contribution by discussing how data analytics governance can contnue to fulfil its purpose of creating (business) value from data. Journal: Journal of Business Analytics Pages: 101-122 Issue: 1 Volume: 5 Year: 2022 Month: 01 X-DOI: 10.1080/2573234X.2021.1955021 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1955021 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:5:y:2022:i:1:p:101-122 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1947751_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Robert Andrews Author-X-Name-First: Robert Author-X-Name-Last: Andrews Author-Name: Fahame Emamjome Author-X-Name-First: Fahame Author-X-Name-Last: Emamjome Author-Name: Arthur H.M. ter Hofstede Author-X-Name-First: Arthur H.M. Author-X-Name-Last: ter Hofstede Author-Name: Hajo A. Reijers Author-X-Name-First: Hajo A. Author-X-Name-Last: Reijers Title: Root-cause analysis of process-data quality problems Abstract: Process mining provides analytical tools and methods which can distil insights about process behaviour from big process-related data. Yet challenges relating to the impact of poor quality data on event logs, the input to process mining analyses, remain. Despite researchers raising concerns about event log data quality, event log preparation is, in practice, generally handled mechanistically, focusing on fixing symptoms rather than on uncovering the root causes of event log data quality issues. To address this, we introduce the Odigos (Greek for “guide”) framework. Based on semiotics and Peircean abductive reasoning, the Odigos framework facilitates an informed way of dealing with data quality issues in event logs. Odigos supports both prognostic (foreshadowing potential quality issues) and diagnostic (identifying root causes of discovered quality issues) approaches. We examine in depth how the framework supports a detailed root-cause analysis of a well-known collection of event log imperfection patterns. Journal: Journal of Business Analytics Pages: 51-75 Issue: 1 Volume: 5 Year: 2022 Month: 01 X-DOI: 10.1080/2573234X.2021.1947751 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1947751 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:5:y:2022:i:1:p:51-75 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1945961_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Martin Fadler Author-X-Name-First: Martin Author-X-Name-Last: Fadler Author-Name: Christine Legner Author-X-Name-First: Christine Author-X-Name-Last: Legner Title: Data ownership revisited: clarifying data accountabilities in times of big data and analytics Abstract: Today, a myriad of data is generated via connected devices and digital applications. In order to benefit from these data, companies have to develop their capabilities related to big data and analytics (BDA). A critical factor that is often cited concerning the “soft” aspects of BDA is data ownership, i.e., clarifying the fundamental rights and responsibilities for data. IS research has investigated data ownership for operational systems and data warehouses, where the purpose of data processing is known. In the BDA context, defining accountabilities for data is more challenging because data are stored in data lakes and used for previously unknown purposes. Based on four case studies, we identify ownership principles and three distinct types: data, data platform, and data product ownership. Our research answers fundamental questions about how data management changes with BDA and lays the foundation for future research on data and analytics governance. Journal: Journal of Business Analytics Pages: 123-139 Issue: 1 Volume: 5 Year: 2022 Month: 01 X-DOI: 10.1080/2573234X.2021.1945961 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1945961 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:5:y:2022:i:1:p:123-139 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2069426_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Christian Janiesch Author-X-Name-First: Christian Author-X-Name-Last: Janiesch Author-Name: Barbara Dinter Author-X-Name-First: Barbara Author-X-Name-Last: Dinter Author-Name: Patrick Mikalef Author-X-Name-First: Patrick Author-X-Name-Last: Mikalef Author-Name: Olgerta Tona Author-X-Name-First: Olgerta Author-X-Name-Last: Tona Title: Business analytics and big data research in information systems Abstract: Business analytics and big data have been at the center of interest for researchers and practitioners for almost a decade now. The methods and processes that comprise business analytics, combined with the rich information that can be extracted from big data have enabled organizations to generate rich insight which is critical to decision making. The scientific inquiry in this interdisciplinary domain has had a long and successful history at the European Conference on Information Systems (ECIS). We provide a synthesis of prominent themes that have appeared during the past decade within the “Business Analytics and Big Data” track of ECIS. Based on the synthesis, we provide a narrative of how the field has evolved, as well as where we see future research efforts being focused. Specifically, we identify three areas that are likely to attract considerable research interest in the years to come. Within each of these three areas, we describe several key challenges that need to be addressed. We conclude with an overview of the six articles included in this special issue, and a description of how they contribute to our understanding of this domain. Journal: Journal of Business Analytics Pages: 1-7 Issue: 1 Volume: 5 Year: 2022 Month: 01 X-DOI: 10.1080/2573234X.2022.2069426 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2069426 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:5:y:2022:i:1:p:1-7 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1978337_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Sven Weinzierl Author-X-Name-First: Sven Author-X-Name-Last: Weinzierl Author-Name: Verena Wolf Author-X-Name-First: Verena Author-X-Name-Last: Wolf Author-Name: Tobias Pauli Author-X-Name-First: Tobias Author-X-Name-Last: Pauli Author-Name: Daniel Beverungen Author-X-Name-First: Daniel Author-X-Name-Last: Beverungen Author-Name: Martin Matzner Author-X-Name-First: Martin Author-X-Name-Last: Matzner Title: Detecting temporal workarounds in business processes – A deep-learning-based method for analysing event log data Abstract: Business process management distinguishes the actual “as-is” and a prescribed “to-be” state of a process. In practice, many different causes trigger a process’s drifting away from its to-be state. For instance, employees may “workaround” the proposed systems to increase their effectiveness or efficiency in day-to-day work. So far, ethnography or critical incident techniques are used to identify how and why workarounds emerge. We design a deep-learning-based method that helps detect different workaround types in event logs. Our method tracks indications of potential workarounds in the early stages of their emergence among deviating behaviour. Our evaluation based on four real-life event logs reveals that our method performs well and works best for business processes with fewer variations and a higher number of different activities. The proposed method is one of the first information technology artefacts to bridge the boundaries between the complementing research disciplines of organisational routines and business processes management. Journal: Journal of Business Analytics Pages: 76-100 Issue: 1 Volume: 5 Year: 2022 Month: 01 X-DOI: 10.1080/2573234X.2021.1978337 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1978337 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:5:y:2022:i:1:p:76-100 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1955022_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Matthias Palmer Author-X-Name-First: Matthias Author-X-Name-Last: Palmer Author-Name: Jan Roeder Author-X-Name-First: Jan Author-X-Name-Last: Roeder Author-Name: Jan Muntermann Author-X-Name-First: Jan Author-X-Name-Last: Muntermann Title: Induction of a sentiment dictionary for financial analyst communication: a data-driven approach balancing machine learning and human intuition Abstract: While sentiment dictionaries are easy to apply and provide reproducible results, they often exhibit inferior classification performance compared to machine learning approaches trained for specific application domains. Nevertheless, both approaches typically require manual data analysis. This paper develops a domain-specific dictionary using regularised linear models drawing from textual reports of financial analysts. The first evaluation step demonstrates that the developed financial analyst dictionary can explain cumulative abnormal stock returns related to earnings events more accurately compared to other finance-related dictionaries and sentiment classifiers. In a second step, the approaches are compared using manually annotated sentiment. The financial analyst dictionary is more accurate than other dictionary-based approaches, although it cannot compete with a pre-trained deep learning sentiment classifier. While we show that the proposed approach is suited for texts of financial analysts, it can be applied to other use cases. The approach realises context specificity while reducing extensive manual data analysis. Journal: Journal of Business Analytics Pages: 8-28 Issue: 1 Volume: 5 Year: 2022 Month: 01 X-DOI: 10.1080/2573234X.2021.1955022 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1955022 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:5:y:2022:i:1:p:8-28 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1952913_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Jonas Wanner Author-X-Name-First: Jonas Author-X-Name-Last: Wanner Author-Name: Lukas-Valentin Herm Author-X-Name-First: Lukas-Valentin Author-X-Name-Last: Herm Author-Name: Kai Heinrich Author-X-Name-First: Kai Author-X-Name-Last: Heinrich Author-Name: Christian Janiesch Author-X-Name-First: Christian Author-X-Name-Last: Janiesch Title: A social evaluation of the perceived goodness of explainability in machine learning Abstract: Machine learning in decision support systems already outperforms pre-existing statistical methods. However, their predictions face challenges as calculations are often complex and not all model predictions are traceable. In fact, many well-performing models are black boxes to the user who– consequently– cannot interpret and understand the rationale behind a model’s prediction. Explainable artificial intelligence has emerged as a field of study to counteract this. However, current research often neglects the human factor. Against this backdrop, we derived and examined factors that influence the goodness of a model’s explainability in a social evaluation of end users. We implemented six common ML algorithms for four different benchmark datasets in a two-factor factorial design and asked potential end users to rate different factors in a survey. Our results show that the perceived goodness of explainability is moderated by the problem type and strongly correlates with trustworthiness as the most important factor. Journal: Journal of Business Analytics Pages: 29-50 Issue: 1 Volume: 5 Year: 2022 Month: 01 X-DOI: 10.1080/2573234X.2021.1952913 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1952913 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:5:y:2022:i:1:p:29-50 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1920856_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Daniel J. Power Author-X-Name-First: Daniel J. Author-X-Name-Last: Power Author-Name: Ciara Heavin Author-X-Name-First: Ciara Author-X-Name-Last: Heavin Author-Name: Yvonne O’Connor Author-X-Name-First: Yvonne Author-X-Name-Last: O’Connor Title: Balancing privacy rights and surveillance analytics: a decision process guide Abstract: The right to privacy has been discussed by scholars in multiple disciplines, yet privacy issues are increasing due to technological advances and lower costs for organisations to adopt smart surveillance. Given the potential for misuse, it seems prudent for stakeholders to critically evaluate Surveillance Analytics (SA) innovations. To assist in balancing the issues arising from SA adoption and the implications for privacy, we review key terms and ethical frameworks. Further, we prescribe a two-by-two Surveillance, Privacy, and Ethical Decision (SPED) Process Guide. SPED recommends the use of one or more of three ethical frameworks, Consequence, Duty, and Virtue. The vertical axis in the SPED matrix is the sophistication of an organisation’s SA and the horizontal axis is an assessment of the current privacy level and the rights afforded to the target(s) of surveillance. The proposed decision process guide can assist senior managers and technologists in making decisions about adopting SA. Journal: Journal of Business Analytics Pages: 155-170 Issue: 2 Volume: 4 Year: 2021 Month: 07 X-DOI: 10.1080/2573234X.2021.1920856 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1920856 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:2:p:155-170 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1943017_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Hokey Min Author-X-Name-First: Hokey Author-X-Name-Last: Min Author-Name: Hey-Young Joo Author-X-Name-First: Hey-Young Author-X-Name-Last: Joo Author-Name: Seok-Beom Choi Author-X-Name-First: Seok-Beom Author-X-Name-Last: Choi Title: Success Factors Affecting the Intention to Use Business Analytics: An Empirical Study Abstract: In the era of knowledge-based economy, the firm’s ability to derive actionable insights from big data can be a game changer. Such ability can be developed and nurtured by utilising BA which is designed to help business executives and policy makers make well-thought and informed decisions. To have a clear picture of what will lead to the serious consideration of BA as a business intelligence tool, this paper identifies contextual variables that include privacy, security, risk concerns, information technology (IT) capability and perceived value that may significantly influence the firm’s intention to use BA. This paper conducted confirmatory factor analyses and used the structural equation model to determine what either motivate or inhibit the BA adoptionThrough a series of hypothesis testing, we discovered that higher security and risk concerns along with a lack of IT capability became important deterrents to BA adoption. Also, we found that firms which recognised the value of BA were more inclined to adopt BA than the others. This paper is one of the first attempts to develop practical guidelines for the potential adopters of BA based on the empirical study of BA practices among the Korean firms. Journal: Journal of Business Analytics Pages: 77-90 Issue: 2 Volume: 4 Year: 2021 Month: 07 X-DOI: 10.1080/2573234X.2021.1943017 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1943017 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:2:p:77-90 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1934128_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Duan C.J. (Chaojie) Author-X-Name-First: Duan C.J. Author-X-Name-Last: (Chaojie) Author-Name: Anuj Gaurav Author-X-Name-First: Anuj Author-X-Name-Last: Gaurav Title: Exposing model bias in machine learning revisiting the boy who cried wolf in the context of phishing detection Abstract: Grown out of the quest for artificial intelligence (AI), machine learning (ML) is today’s most active field across disciplines with a sharp increase in applications ranging from criminology to fraud detection and to biometrics. ML and statistics both emphasise model estimation/training and thus share the inescapable Type 1 and 2 errors. Extending the concept of statistical errors into the domain of ML, we devise a ground-breaking pH scale-like ratio and intend it as a litmus test indicator of ML model bias completely masked by the popular performance criterion of accuracy. Using publicly available phishing dataset, we conduct experiments on a series of classification models and consequently unravel the significant cost implications of models with varying levels of bias. Based on these results, we recommend practitioners exercise human judgement and match their own risk tolerance profile with the bias ratio associated with each ML model in order to guard against potential unintended adverse effects. Journal: Journal of Business Analytics Pages: 171-178 Issue: 2 Volume: 4 Year: 2021 Month: 07 X-DOI: 10.1080/2573234X.2021.1934128 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1934128 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:2:p:171-178 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1970483_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Rajiv Sambasivan Author-X-Name-First: Rajiv Author-X-Name-Last: Sambasivan Title: Revenue characterisation with Singular Spectrum Analysis Abstract: In this work, a method to characterise the daily sales revenue for an online store is presented. Daily sales revenue is a time series. The developed characterisation identifies the major sources of variation in the time series. Such a characterisation can be used for purposes such as developing structural forecasting models and extracting insights that can be leveraged for business and operations planning. In this work, this characterisation is developed using a technique called Singular Spectrum Analysis. Achieving good results with Singular Spectrum Analysis requires the judicious selection of an algorithm parameter called the window length. A framework to select this parameter is provided. Literature survey revealed that applications of Singular Spectrum Analysis to business data are limited. To the best of found knowledge from the literature survey, Singular Spectrum Analysis has not been applied to retail revenue stream analysis. Journal: Journal of Business Analytics Pages: 140-154 Issue: 2 Volume: 4 Year: 2021 Month: 07 X-DOI: 10.1080/2573234X.2021.1970483 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1970483 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:2:p:140-154 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1947752_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Venil P. Author-X-Name-First: Venil Author-X-Name-Last: P. Author-Name: Vinodhini G. Author-X-Name-First: Vinodhini Author-X-Name-Last: G. Author-Name: K. Suresh Joseph Author-X-Name-First: K. Suresh Author-X-Name-Last: Joseph Title: A Combined Approach For Collaborative Filtering Based Recommender Systems with Matrix Factorisation and Outlier Detection Abstract: Recommender system is a data sifting tool that can recommend items that can be of interest to the user. Collaborative filtering (CF) makes recommendations based on the ratings the users give to items. But noisy or inaccurate ratings reduce the quality of the recommendations. In spite of extensive studies carried on CF-based recommenders, a robust recommender to handle outlier in dataset is a challenging problem. In this study, a Factor wise Matrix Factorisation model (FWMF) is proposed for the prediction of item rating in recommender systems. To further strengthen the proposed FWMF model, a meta learning model that combines density-based outlier detection and bagging outlier detection is proposed to detect outliers. The outliers predicted are eliminated, and a comparative analysis is carried with FWMF to find the effect of outliers in making recommendations. The experiments were analysed with various error metrics conducted on benchmark dataset show that the proposed outlier extent recommendation model outperforms the conventional CF-based systems. Journal: Journal of Business Analytics Pages: 111-124 Issue: 2 Volume: 4 Year: 2021 Month: 07 X-DOI: 10.1080/2573234X.2021.1947752 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1947752 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:2:p:111-124 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1937351_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Kazim Topuz Author-X-Name-First: Kazim Author-X-Name-Last: Topuz Author-Name: Brett D. Jones Author-X-Name-First: Brett D. Author-X-Name-Last: Jones Author-Name: Sumeyra Sahbaz Author-X-Name-First: Sumeyra Author-X-Name-Last: Sahbaz Author-Name: Murad Moqbel Author-X-Name-First: Murad Author-X-Name-Last: Moqbel Title: Methodology to combine theoretical knowledge with a data-driven probabilistic graphical model Abstract: This study presents an analytic inference methodology using probabilistic modeling that provides faster decision-making and a better understanding of complex relations. Two educational psychology models (i.e., the MUSIC Model of Motivation and the domain identification model) were coupled with a data-driven Probabilistic Graphical Model to provide a top-down and bottom-up combination for reasoning. Using survey data from middle school students, Bayesian Network models captured the probabilistic interactions between students’ perceptions of their science class, their identification with science, and their science career goals. Complex/non-linear relationships among these variables revealed that students’ perceptions of their science class (i.e., eMpowerment, Usefulness, Success, Interest, and Caring) were significant predictors of their science-related career goals. These findings provide validity evidence for using the MUSIC and domain identification models and provide educators and school administrators with a web-based simulator to estimate the effect of students’ science class perceptions on their science identification and career goals. Journal: Journal of Business Analytics Pages: 125-139 Issue: 2 Volume: 4 Year: 2021 Month: 07 X-DOI: 10.1080/2573234X.2021.1937351 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1937351 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:2:p:125-139 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1908861_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Christoph Sager Author-X-Name-First: Christoph Author-X-Name-Last: Sager Author-Name: Christian Janiesch Author-X-Name-First: Christian Author-X-Name-Last: Janiesch Author-Name: Patrick Zschech Author-X-Name-First: Patrick Author-X-Name-Last: Zschech Title: A survey of image labelling for computer vision applications Abstract: Supervised machine learning methods for image analysis require large amounts of labelled training data to solve computer vision problems. The recent rise of deep learning algorithms for recognising image content has led to the emergence of many ad-hoc labelling tools. With this survey, we capture and systematise the commonalities as well as the distinctions between existing image labelling software. We perform a structured literature review to compile the underlying concepts and features of image labelling software such as annotation expressiveness and degree of automation. We structure the manual labelling task by its organisation of work, user interface design options, and user support techniques to derive a systematisation schema for this survey. Applying it to available software and the body of literature, enabled us to uncover several application archetypes and key domains such as image retrieval or instance identification in healthcare or television. Journal: Journal of Business Analytics Pages: 91-110 Issue: 2 Volume: 4 Year: 2021 Month: 07 X-DOI: 10.1080/2573234X.2021.1908861 File-URL: http://hdl.handle.net/10.1080/2573234X.2021.1908861 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:4:y:2021:i:2:p:91-110 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1507527_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Sudha Ram Author-X-Name-First: Sudha Author-X-Name-Last: Ram Author-Name: Dursun Delen Author-X-Name-First: Dursun Author-X-Name-Last: Delen Title: Introduction to the inaugural issue of Journal of Business Analytics Journal: Journal of Business Analytics Pages: 1-1 Issue: 1 Volume: 1 Year: 2018 Month: 1 X-DOI: 10.1080/2573234X.2018.1507527 File-URL: http://hdl.handle.net/10.1080/2573234X.2018.1507527 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:1:y:2018:i:1:p:1-1 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1507324_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Dursun Delen Author-X-Name-First: Dursun Author-X-Name-Last: Delen Author-Name: Sudha Ram Author-X-Name-First: Sudha Author-X-Name-Last: Ram Title: Research challenges and opportunities in business analytics Abstract: There are plenty of definitions proposed for business analytics – some of them focus on the scope/coverage/problem, some on the nature of the data, and some concentrate on the enabling methods and methodologies. The common denominator of all of these definitions is that business analytics is the encapsulation of all mechanisms that help convert data into actionable insight for better and faster decision-making. Although the name is new, its purpose has been around for several decades, characterised under different labels. Largely driven by the need in the business world, business analytics has become one of the most active research areas in academics and in industry/practice. The Journal of Business Analytics is created to establish a dedicated home for analytics researchers to publish their research outcomes. Covering all facets of business analytics (descriptive/diagnostic, predictive, and prescriptive), the journal is destined to become the pinnacle for rigorous and relevant analytics research manuscripts. Herein we provide an overview of research challenges and opportunities for business analytics to lay the groundwork for this new journal. Journal: Journal of Business Analytics Pages: 2-12 Issue: 1 Volume: 1 Year: 2018 Month: 1 X-DOI: 10.1080/2573234X.2018.1507324 File-URL: http://hdl.handle.net/10.1080/2573234X.2018.1507324 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:1:y:2018:i:1:p:2-12 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1506686_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Juan Qin Author-X-Name-First: Juan Author-X-Name-Last: Qin Author-Name: Stephanie Lee Author-X-Name-First: Stephanie Author-X-Name-Last: Lee Author-Name: Xiangbin Yan Author-X-Name-First: Xiangbin Author-X-Name-Last: Yan Author-Name: Yong Tan Author-X-Name-First: Yong Author-X-Name-Last: Tan Title: Beyond solving the last mile problem: the substitution effects of bike-sharing on a ride-sharing platform Abstract: Ride-sharing services have been popularly used for both short-distance and long-distance trips. The recent introduction and growth of bike-sharing services can help solve the last mile problem and provide a good mobility option, especially for short-distance travellers. We examine the extent to which bike-sharing platforms solve the last mile problem and affect short-distance travels by studying their impacts on ride-sharing orders. To do so, we exploit a natural experiment setting in which bike-sharing platforms were newly launched in Chengdu, China. We combine detailed granular one-month order data collected from DiDi with Chengdu’s geographic information data from Gaode Map, a Chinese leading map provider. We find that the introduction of bike-sharing platforms significantly reduces short-distance ride-sharing orders. We additionally examine the heterogeneity in substitution effects across different pickup and drop-off locations and find that location attributes significantly affect bike-sharing’s substitution effects on ride-sharing platforms. Journal: Journal of Business Analytics Pages: 13-28 Issue: 1 Volume: 1 Year: 2018 Month: 1 X-DOI: 10.1080/2573234X.2018.1506686 File-URL: http://hdl.handle.net/10.1080/2573234X.2018.1506686 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:1:y:2018:i:1:p:13-28 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1506687_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Swayambhu Chatterjee Author-X-Name-First: Swayambhu Author-X-Name-Last: Chatterjee Author-Name: Shuyuan Deng Author-X-Name-First: Shuyuan Author-X-Name-Last: Deng Author-Name: Jun Liu Author-X-Name-First: Jun Author-X-Name-Last: Liu Author-Name: Ronghua Shan Author-X-Name-First: Ronghua Author-X-Name-Last: Shan Author-Name: Wu Jiao Author-X-Name-First: Wu Author-X-Name-Last: Jiao Title: Classifying facts and opinions in Twitter messages: a deep learning-based approach Abstract: Massive social media data present businesses with an immense opportunity to extract useful insights. However, social media messages typically consist of both facts and opinions, posing a challenge to analytics applications that focus more on either facts and opinions. Distinguishing facts and opinionss may significantly improve subsequent analytics tasks. In this study, we propose a deep learning-based algorithm that automatically separates facts from opinions in Twitter messages. The algorithm outperformed multiple popular baselines in an experiment we conducted. We further applied the proposed algorithm to track customer complaints and found that it indeed benefits subsequent analytics applications. Journal: Journal of Business Analytics Pages: 29-39 Issue: 1 Volume: 1 Year: 2018 Month: 1 X-DOI: 10.1080/2573234X.2018.1506687 File-URL: http://hdl.handle.net/10.1080/2573234X.2018.1506687 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:1:y:2018:i:1:p:29-39 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1507605_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: D. J. Power Author-X-Name-First: D. J. Author-X-Name-Last: Power Author-Name: C. Heavin Author-X-Name-First: C. Author-X-Name-Last: Heavin Author-Name: J. McDermott Author-X-Name-First: J. Author-X-Name-Last: McDermott Author-Name: M. Daly Author-X-Name-First: M. Author-X-Name-Last: Daly Title: Defining business analytics: an empirical approach Abstract: Searches of the Web using Google, and database searches of the academic and practitioner literature, return a large number of differing and varied definitions of the concept of business analytics. This article reviews the growing literature on Business Analytics (BA) using traditional and qualitative research tools. Our searches included using Google Search to identify examples of business analytics applications, and a focused keyword search of the available practitioner and academic literatures. Text analytics techniques identified frequently used terms in prior definitions of business analytics. Our empirical, inductive approach provides a basis for proposing and explaining a formal sentence definition for Business Analytics. The analysis provides a starting point for operationalising a measure for the business analytics construct. Additionally, understanding business analytics can help managers assess skill deficiencies and evaluate claims about relevance of tools and techniques. Finally, carefully defining the Business Analytics concept should provide stimulus for new research ideas. Journal: Journal of Business Analytics Pages: 40-53 Issue: 1 Volume: 1 Year: 2018 Month: 1 X-DOI: 10.1080/2573234X.2018.1507605 File-URL: http://hdl.handle.net/10.1080/2573234X.2018.1507605 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:1:y:2018:i:1:p:40-53 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1507604_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Jie Tao Author-X-Name-First: Jie Author-X-Name-Last: Tao Author-Name: Amit V. Deokar Author-X-Name-First: Amit V. Author-X-Name-Last: Deokar Author-Name: Ashutosh Deshmukh Author-X-Name-First: Ashutosh Author-X-Name-Last: Deshmukh Title: Analysing forward-looking statements in initial public offering prospectuses: a text analytics approach Abstract: Forward-looking statements (FLSs) have informational value in applications such as predicting stock prices. Management Discussion & Analysis (MD&A) sections in initial public offering (IPO) prospectuses contain FLSs that provide prospective information about the company’s future growth and performance. This study focuses on evaluating the relationship between features extracted from FLSs and IPO valuation. To that end, we propose an analytical pipeline for identifying FLSs using machine learning techniques. The FLS classifier is built on the best performing deep learning architecture that outperforms extant methods reported in related studies. In order to demonstrate the value of identified FLSs, we conduct predictive analysis of pre-IPO price revisions and post-IPO first-day returns. We engineer a variety of linguistics features from FLSs including topics, sentiments, readability, semantic similarity, and general text features. The study finds that FLS features are more predictive for pre-IPO as compared to post-IPO valuation prediction. The analytical pipeline contributes to the text classification knowledge base while the findings from the predictive analysis shed light on understanding the underpricing phenomenon occurring in the IPO process. Journal: Journal of Business Analytics Pages: 54-70 Issue: 1 Volume: 1 Year: 2018 Month: 1 X-DOI: 10.1080/2573234X.2018.1507604 File-URL: http://hdl.handle.net/10.1080/2573234X.2018.1507604 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:1:y:2018:i:1:p:54-70 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_1590035_J.xml processed with: repec_from_tfjats.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: The Editors Title: Correction Journal: Journal of Business Analytics Pages: 71-71 Issue: 1 Volume: 1 Year: 2018 Month: 1 X-DOI: 10.1080/2573234X.2019.1590035 File-URL: http://hdl.handle.net/10.1080/2573234X.2019.1590035 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:1:y:2018:i:1:p:71-71 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2167670_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Takumi Kato Author-X-Name-First: Takumi Author-X-Name-Last: Kato Author-Name: Susumu Kamei Author-X-Name-First: Susumu Author-X-Name-Last: Kamei Author-Name: Takumi Ootsubo Author-X-Name-First: Takumi Author-X-Name-Last: Ootsubo Author-Name: Yosuke Ichiki Author-X-Name-First: Yosuke Author-X-Name-Last: Ichiki Title: More information is not better: examining appropriate information for estimating sales performance in concept testing Abstract: Research on the requirements for improving the quality of concept testing is scarce because of the high degree of confidentiality in new product developments. In this study, we clarified the factors that can improve sales performance estimation accuracy in concept testing. A randomised controlled trial for the Japanese personal computer market showed that presenting the product and corporate brand yielded the most accurate estimations. Other factors (design, price, and product colour) did not show significant effects. Even a good concept may not increase consumers’ purchase intention if there is lack of clarity about the product’s brand. Journal: Journal of Business Analytics Pages: 188-202 Issue: 3 Volume: 6 Year: 2023 Month: 07 X-DOI: 10.1080/2573234X.2023.2167670 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2167670 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:3:p:188-202 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2155257_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Sathyendra Singh Chauhan Author-X-Name-First: Sathyendra Author-X-Name-Last: Singh Chauhan Author-Name: Karthik Srinivasan Author-X-Name-First: Karthik Author-X-Name-Last: Srinivasan Author-Name: Tarun Sharma Author-X-Name-First: Tarun Author-X-Name-Last: Sharma Title: A trans-national comparison of stock market movements and related social media chatter during the COVID-19 pandemic Abstract: The outbreak of the SARS-CoV-2 (COVID-19) pandemic first identified in 2019 has had long-term ramifications across global financial markets. We have seen stock markets across countries falling to historical lows and then recovering back during the pandemic. Prior research has established that human emotions can significantly influence financial markets. In particular, social media discussions or online Word-of-mouth (OWoM) minutely reflect public emotions and opinions associated with global market volatility. In this study, we use a quantitative approach to explore the relationship between discussions in twitter, a popular micro-blogging online platform and stock market performance across different countries, in order to understand the disaster-triggered behavioural responses of common investors across the globe. We analyse the association of national stock-indices, sentiment polarity and discussion subjectivity in Covid-19-related tweets originating in India, US, Italy, UK, Australia, Nigeria and South Africa during February 2020– January 2021 period. Using a combination of multiple analytics methods, our study examines: (i) linear and lagged association between OWoM and market performance; and (ii) heterogeneity in the OWoM-market relationship across the seven countries. Our results show weak but statistically significant correlation between OWoM subjectivity and polarity and stock market returns across countries. Our findings also show differential temporal association of OWoM and market returns across countries. Our study shows stock market connectedness between pairs of countries, some simultaneously varying while others varying with a time lag, and the strength of such connectedness increases during global disasters such as the COVID-19 pandemic. Journal: Journal of Business Analytics Pages: 203-216 Issue: 3 Volume: 6 Year: 2023 Month: 07 X-DOI: 10.1080/2573234X.2022.2155257 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2155257 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:3:p:203-216 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2122881_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Milton Soto-Ferrari Author-X-Name-First: Milton Author-X-Name-Last: Soto-Ferrari Author-Name: Alejandro Carrasco-Pena Author-X-Name-First: Alejandro Author-X-Name-Last: Carrasco-Pena Author-Name: Diana Prieto Author-X-Name-First: Diana Author-X-Name-Last: Prieto Title: AGGFORCLUS: A hybrid methodology integrating forecasting with clustering to assess mitigation plans and contagion risk in pandemic outbreaks: the COVID-19 Case Study Abstract: The COVID-19 pandemic showed governments’ unpreparedness as decision-makers hastily created restrictions and policies to contain its spread. Identifying prospective areas with a higher contagion risk can reduce mitigation planning uncertainty. This research proposes a risk assessment metric called AGGFORCLUS that integrates time-series forecasting and clustering to convey joint information on predicted caseload growth and variability, thereby providing an educated yet visually simple view of the risk status. In AGGFORCLUS, the development is sectioned into three phases. Phase I forecasts confirmed cases using a mixture of five different forecasting methods. Phase II develops the identified best model forecasts for an extended ten-day horizon, including their prediction intervals. In Phase III, we calculate average growth metrics for predictions and use them to cluster series by their multidimensional average growth. We present the results for various countries framed into a nine-quadrant risk-grouped associated measure linked to the expected cumulative caseload progress and uncertainty. Journal: Journal of Business Analytics Pages: 217-242 Issue: 3 Volume: 6 Year: 2023 Month: 07 X-DOI: 10.1080/2573234X.2022.2122881 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2122881 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:3:p:217-242 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2136541_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Hong Qin Author-X-Name-First: Hong Author-X-Name-Last: Qin Author-Name: Kai Koong Author-X-Name-First: Kai Author-X-Name-Last: Koong Author-Name: Haoyu Wen Author-X-Name-First: Haoyu Author-X-Name-Last: Wen Author-Name: Lai Liu Author-X-Name-First: Lai Author-X-Name-Last: Liu Title: Mapping business analytics skillsets with industries: empirical evidence from online job advertisements Abstract: As a large accumulation of data is captured and contained, organisations find that the invaluable information can be used to improve company performance, leverage competitive advantages, and create business values. Using business analytics (BA) job advertisements collected from a recruiting website, this study identified knowledge domains and skillsets of BA professionals. Additionally, it examined the relative importance of these BA skills in different industries such as Financial and Information Technology services. The results of Text mining analysis indicate that data modelling, statistical software, visualisation, forecasting, and database are the top ranked BA technical skills. In addition, process skills such as communication, project management, and financial techniques are crucial. The association rules analysis recognises the relative importance of BA skillsets across different industries. The findings contribute to the employability and professional development of new graduates; additionally, they provide insights to BA academic curriculum design and human resources management. Journal: Journal of Business Analytics Pages: 167-179 Issue: 3 Volume: 6 Year: 2023 Month: 07 X-DOI: 10.1080/2573234X.2022.2136541 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2136541 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:3:p:167-179 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2128447_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Mehmet Serdar Kilinc Author-X-Name-First: Mehmet Serdar Author-X-Name-Last: Kilinc Author-Name: Robert Rohrhirsch Author-X-Name-First: Robert Author-X-Name-Last: Rohrhirsch Title: Predicting customers’ cross-buying decisions: a two-stage machine learning approach Abstract: Predicting a customer’s cross-buying behaviour is a challenging problem for many organisations. In this paper, we propose a novel two-stage cross-buying prediction framework by integrating machine learning, feature engineering, and interpretation techniques. Specifically, the first stage aims to train an accurate complex black-box classification model with cross-validation and hyperparameter tuning. Then, the next stage uses the top ten most important predictors of the black-box model to obtain a simple rule-based interpretable model. We use a publicly available dataset published on the Harvard Dataverse to provide a practical case study. The results show that the rule-based model has a predictive performance as high as the complex model. Journal: Journal of Business Analytics Pages: 180-187 Issue: 3 Volume: 6 Year: 2023 Month: 07 X-DOI: 10.1080/2573234X.2022.2128447 File-URL: http://hdl.handle.net/10.1080/2573234X.2022.2128447 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:3:p:180-187 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2202691_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Seyed Mohsen Mousavi Author-X-Name-First: Seyed Mohsen Author-X-Name-Last: Mousavi Author-Name: Kiarash Sadeghi R. Author-X-Name-First: Kiarash Author-X-Name-Last: Sadeghi R. Author-Name: Lai Soon Lee Author-X-Name-First: Lai Soon Author-X-Name-Last: Lee Title: An interactive analytics approach for sustainable and resilient case studies: a machine learning perspective Abstract: Sustainable development is a problem-solving method that simultaneously accounts for the economic, environmental, and social impacts of actions. Decision-makers have recently recognised the need for sustainable development. Multiobjective optimisation is the most reliable technique to solve multiple sustainable development goals. However, there needs to be more research examining the role of interactive methods in multiobjective optimisation problems. To integrate machine learning and human interactions, this paper develops a new three-stage interactive algorithm in business analytics, called the interactive Nautilus-based algorithm, to address complex problems. To show the method’s applicability, this paper uses the proposed algorithm in three sustainable and resilient case studies. The selected cases are the river pollution problem, the urban transit network design problem, and the resilience problem. Moreover, the proposed algorithm is compared with two other algorithms for validation purposes. The results reveal that the proposed algorithm outperforms non-interactive algorithms by providing superior solutions. Journal: Journal of Business Analytics Pages: 276-293 Issue: 4 Volume: 6 Year: 2023 Month: 10 X-DOI: 10.1080/2573234X.2023.2202691 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2202691 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:4:p:276-293 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2193224_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Wajdi Frikha Author-X-Name-First: Wajdi Author-X-Name-Last: Frikha Author-Name: Mariem Brahim Author-X-Name-First: Mariem Author-X-Name-Last: Brahim Author-Name: Ahmed Jeribi Author-X-Name-First: Ahmed Author-X-Name-Last: Jeribi Author-Name: Amine Lahiani Author-X-Name-First: Amine Author-X-Name-Last: Lahiani Title: COVID-19, Russia-Ukraine war and interconnectedness between stock and crypto markets: a wavelet-based analysis Abstract: This paper aims to investigate the impacts of the COVID-19 pandemic and Russia-Ukraine war on the interconnectedness between the US and China stock markets, major cryptocurrency and commodity markets using the wavelet coherence approach over the period from January 1 2016 to April 18 2022. The aim is to understand how the COVID-19 pandemic and the Russia-Ukraine war have affected the hedging efficiency of volatile crypto-currencies and gold. Wavelet coherency analysis unveils perceptual differences between the short-term and longer-term market reactions. In the short-run, we find strong co-movements during the first and second waves of the pandemic. During the first wave, longer-term investors were driven by the belief of future pandemic demise. They make use of time diversification that results in positive returns. During the Russia-Ukraine war, S&P 500 leads Bitcoin, BNB, and Ripple whereas Ethereum leads S&P 500 and SSE. Journal: Journal of Business Analytics Pages: 255-275 Issue: 4 Volume: 6 Year: 2023 Month: 10 X-DOI: 10.1080/2573234X.2023.2193224 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2193224 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:4:p:255-275 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2186274_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Annelien Crijns Author-X-Name-First: Annelien Author-X-Name-Last: Crijns Author-Name: Victor Vanhullebusch Author-X-Name-First: Victor Author-X-Name-Last: Vanhullebusch Author-Name: Manon Reusens Author-X-Name-First: Manon Author-X-Name-Last: Reusens Author-Name: Michael Reusens Author-X-Name-First: Michael Author-X-Name-Last: Reusens Author-Name: Bart Baesens Author-X-Name-First: Bart Author-X-Name-Last: Baesens Title: Topic modelling applied on innovation studies of Flemish companies Abstract: Mapping innovation in companies for the purpose of official statistics is usually done through business surveys. However, this traditional approach faces several drawbacks like a lack of responses, response bias, low frequency, and high costs. Alternatively, text-based models trained on web-scraped text from company websites have been developed to complement or substitute traditional business surveys. This paper utilises web scraping and text-based models to map the business innovation in Flanders with a focus on identifying different types of innovation through topic modelling. More specifically, the scraped web texts are used to identify innovative economic sectors or topics, and to classify firms into these topics using Top2Vec and Lbl2Vec. We conclude that both models can be successfully combined to discover topics (or sectors) and classify companies into these topics which results in an additional parameter for mapping innovation in different regions. Journal: Journal of Business Analytics Pages: 243-254 Issue: 4 Volume: 6 Year: 2023 Month: 10 X-DOI: 10.1080/2573234X.2023.2186274 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2186274 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:4:p:243-254 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2204159_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20230119T200553 git hash: 724830af20 Author-Name: Mohammad Daneshvar Kakhki Author-X-Name-First: Mohammad Author-X-Name-Last: Daneshvar Kakhki Author-Name: Utkarsh Shrivastava Author-X-Name-First: Utkarsh Author-X-Name-Last: Shrivastava Title: Data analytics management capability and strategies for interorganisational collaborations: a survey research Abstract: Drawing on the dynamic capabilities perspective, we propose a research model that explains how data analytics management capability (DAMC) impacts interorganisational collaboration and business performance. Our model incorporates DA strategy as a moderator of the relationship between DAMC and collaboration. We test our model with a survey of 508 practitioners. Our findings suggest that while the DA innovator strategy fosters collaboration, it does not improve performance. In contrast, a more conservative DA strategy leads to higher strategic and operational performance. Our work highlights how leveraging DAMC facilitates effective interorganisational collaborations. Journal: Journal of Business Analytics Pages: 294-314 Issue: 4 Volume: 6 Year: 2023 Month: 10 X-DOI: 10.1080/2573234X.2023.2204159 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2204159 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:6:y:2023:i:4:p:294-314 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2239877_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20231214T103247 git hash: d7a2cb0857 Author-Name: Harrison Bohl Author-X-Name-First: Harrison Author-X-Name-Last: Bohl Author-Name: Jasmine Craig Author-X-Name-First: Jasmine Author-X-Name-Last: Craig Author-Name: Evan Shellshear Author-X-Name-First: Evan Author-X-Name-Last: Shellshear Title: A Shapley-value Index for Market Basket Analysis: Weighting Shapley’s Value Abstract: The SIMBA (Shapley value Index for Market Basket Analysis) approach aims to calculate the average revenue generated by an item, including additional revenue from items commonly purchased alongside it. Real-world experimentation in SMCG (Slow Moving Consumer Goods) environments has highlighted the limitations of this method. A novel approach called SIMBAW (Weighted SIMBA) is introduced in this paper, which uses an adapted Shapley value to overcome the aforementioned limitation. The SIMBAW approach weighs items’ Shapley values, and therefore their total attributed values, based on the frequency at which they are the most expensive purchase in their basket and therefore how likely they are to drive their basket in a SMCG scenario. The effectiveness of this approach is evaluated on the same dataset highlighting the improved value assigned to non-basket-driver items over SIMBA. SIMBAW will provide SMCG retailers with an accurate representation of the total revenue generated by an item. Journal: Journal of Business Analytics Pages: 15-24 Issue: 1 Volume: 7 Year: 2024 Month: 01 X-DOI: 10.1080/2573234X.2023.2239877 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2239877 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:7:y:2024:i:1:p:15-24 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2248203_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20231214T103247 git hash: d7a2cb0857 Author-Name: Budhi S. Wibowo Author-X-Name-First: Budhi S. Author-X-Name-Last: Wibowo Title: When and how to adjust statistical forecasts in supply chains? Insight from causal machine learning Abstract: Empirical studies have discovered that most statistical forecasts in supply chains are subjected to judgemental adjustments during a forecast review. Although such a practice requires significant management effort and frequently reduces forecast accuracy, many organisations prefer this approach as part of their Sales & Operations Planning process. This study aims to identify the optimal policy to achieve significant accuracy improvement from forecast review. We focus on a practical situation where managers periodically review forecasts from the statistical software and compare them with judgemental forecasts from the sales and marketing functions. Managers must decide whether to disregard the judgement and continue with the existing forecast or revise the statistical forecast based on the judgement. To determine the best course of action, we conducted a numerical experiment using data from five supply-chain companies wit more than 12,000-point forecasts. The experiment considered three alternative actions: “do-nothing”, “follow the judgement”, and “simple-average”. Using a causal machine learning method, namely a policy tree, we develop a set of decision rules that maximise the expected accuracy gains given the variation in forecasting features. The result proposes a simple yet effective policy to recommend suitable actions based on two identified key features: “judgment direction” and the “accuracy of statistical forecasts”. The policy was tested against real-world data and achieved remarkable accuracy with roughly a 3–11 percentage points improvement over the baseline. Our findings offer valuable insights for managers to customise their forecast review policy based on their unique environment. Journal: Journal of Business Analytics Pages: 25-41 Issue: 1 Volume: 7 Year: 2024 Month: 01 X-DOI: 10.1080/2573234X.2023.2248203 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2248203 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:7:y:2024:i:1:p:25-41 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2231966_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20231214T103247 git hash: d7a2cb0857 Author-Name: Ghulam Muhammad Author-X-Name-First: Ghulam Author-X-Name-Last: Muhammad Author-Name: Muddassir Sayeed Siddiqui Author-X-Name-First: Muddassir Sayeed Author-X-Name-Last: Siddiqui Author-Name: Rizwana Rasheed Author-X-Name-First: Rizwana Author-X-Name-Last: Rasheed Author-Name: Heena Shabbir Author-X-Name-First: Heena Author-X-Name-Last: Shabbir Author-Name: Rabia Falak Sher Author-X-Name-First: Rabia Falak Author-X-Name-Last: Sher Title: Role of External Factors in Adoption of HR Analytics: Does Statistical Background, Gender and Age Matters? Abstract: This research investigates the impact of external factors on the adoption of Human Resource Analytics (HRA) under the framework of original UTAUT model. The conceptual framework of four independent variables under the rubric of external factors that may influence the adoption of HRA is grounded in literature’s recommendations for future studies. The study further investigated Gender, Age and Statistical Background as control variables. The sample for the research includes 123 responses from the HR professionals in Pakistan’s Banking Sector. The collected data were analysed by using SmartPLS V. 3.2.8. The findings obtained from the study confirms that Social Influence and Statistical Background are the significant factors that influence the adoption of HRA among HR professionals. Besides this, the control variable “statistical background” appeared to have been influencing the relationship between Social Influence and HRA. The results further included the academic and practical implications of the study. Journal: Journal of Business Analytics Pages: 1-14 Issue: 1 Volume: 7 Year: 2024 Month: 01 X-DOI: 10.1080/2573234X.2023.2231966 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2231966 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:7:y:2024:i:1:p:1-14 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2263522_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20231214T103247 git hash: d7a2cb0857 Author-Name: Mahmut Sami Sivri Author-X-Name-First: Mahmut Sami Author-X-Name-Last: Sivri Author-Name: Alp Ustundag Author-X-Name-First: Alp Author-X-Name-Last: Ustundag Title: An adaptive and enhanced framework for daily stock market prediction using feature selection and ensemble learning algorithms Abstract: Even a slight increase in accuracy when predicting the direction of stock movements can have a significant impact on the rate of returns. However, determining the most suitable variables, methods, and parameters to predict price changes is extremely challenging due to the multitude of variables influencing these changes. This paper presents an innovative prediction framework that combines ensemble learning and feature selection algorithms to effectively capture daily stock movements. The study focuses on predicting the change between the opening and closing prices of the subsequent day and employs a daily sliding window cross-validation methodology. The framework comprises fourteen variable groups encompassing a range of financial and operational indicators. Experimental findings indicate that a competitive performance was achieved for stocks within the Borsa Istanbul 30 index. Light Gradient Boosting Machines and Shapley Additive Explanations emerges as the optimal model combination and exhibits superior performance compared to a buy-and-hold strategy. Journal: Journal of Business Analytics Pages: 42-62 Issue: 1 Volume: 7 Year: 2024 Month: 01 X-DOI: 10.1080/2573234X.2023.2263522 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2263522 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:7:y:2024:i:1:p:42-62 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2292536_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20240209T083504 git hash: db97ba8e3a Author-Name: Marina E. Johnson Author-X-Name-First: Marina E. Author-X-Name-Last: Johnson Author-Name: Ross A. Malaga Author-X-Name-First: Ross A. Author-X-Name-Last: Malaga Title: Exploring the relationship between YouTube video optimisation practices and video rankings for online marketing: a machine learning approach Abstract: YouTube plays a vital role in allowing firms to engage with customers and digitally market their products. Many firms operating on major e-commerce platforms (e.g., eBay and Amazon) rely on advertising their products on YouTube by creating video content providing product information. Hence, there is an increasing need for research to examine the various aspects of YouTube videos for better ranking and views. This research develops a framework through machine learning to predict if a particular video will rank in the top 10 on a YouTube search. This research investigates factors affecting video rankings via a post-model agnostic technique called Shapley Additive Explanations (SHAP) and sentiment analysis. The results show that video content creators should optimise video titles and descriptions with the keywords of interest. Creators should consider the sentiment of the description and strive for a positive tone. Finally, creators should solicit views and likes to obtain better rankings. Journal: Journal of Business Analytics Pages: 120-135 Issue: 2 Volume: 7 Year: 2024 Month: 04 X-DOI: 10.1080/2573234X.2023.2292536 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2292536 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:7:y:2024:i:2:p:120-135 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2285483_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20240209T083504 git hash: db97ba8e3a Author-Name: Mutaz M. Al-Debei Author-X-Name-First: Mutaz M. Author-X-Name-Last: Al-Debei Title: The era of business analytics: identifying and ranking the differences between business intelligence and data science from practitioners’ perspective using the Delphi method Abstract: The concepts associated with business analytics, such as business intelligence and data science, are generally murky. However, this misconception has a harmful impact on both academics and practitioners. This uncertainty may cause universities to develop misleading or incoherent curricula. This lack of clarity may also cause enterprises to choose an inappropriate analytical solution to a business problem, resulting in project failure and wasted resources. Despite its significance; it appears that only practitioners and major consulting firms are exerting significant effort to address this matter. Hence, this study aims to fill this void and uses the Delphi method to indicate that business intelligence and data science may be classified using eight dimensions which are: types of analytics, analytics process, skill set, data sources, business value, the scope of analytics, methods & techniques, and finally, technological platforms & tools. Significant implications for theory and practice are offered. Journal: Journal of Business Analytics Pages: 94-119 Issue: 2 Volume: 7 Year: 2024 Month: 04 X-DOI: 10.1080/2573234X.2023.2285483 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2285483 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:7:y:2024:i:2:p:94-119 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2281317_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20240209T083504 git hash: db97ba8e3a Author-Name: Leila Taherkhani Author-X-Name-First: Leila Author-X-Name-Last: Taherkhani Author-Name: Amir Daneshvar Author-X-Name-First: Amir Author-X-Name-Last: Daneshvar Author-Name: Hossein Amoozad Khalili Author-X-Name-First: Hossein Author-X-Name-Last: Amoozad Khalili Author-Name: Mohammad Reza Sanaei Author-X-Name-First: Mohammad Reza Author-X-Name-Last: Sanaei Title: Intelligent decision support system using nested ensemble approach for customer churn in the hotel industry Abstract: Since customer retention costs much less than attracting new customer, the problem of customer churn is a major challenge in various fields of work and particularly Hotel Industry. In this research, a solution based on an intelligent decision support system using text mining and nested ensemble techniques is presented, which combines the advantages of stacking and voting methods. In the proposed system, after the text mining of the data collected from the hotels of Kish Island, the effective feature selection is done using the gravity search algorithm. In the first level of nested ensemble technique method, stacking deep learning methods are used. Voting is used in the MetaClassifier section, which includes Random Forest, Xgboost and Naïve Bayes methods. The results of the implementation and comparison of the proposed system, show that the performance of the proposed system has increased the accuracy by 0.04 compared to the best existing method. Journal: Journal of Business Analytics Pages: 83-93 Issue: 2 Volume: 7 Year: 2024 Month: 04 X-DOI: 10.1080/2573234X.2023.2281317 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2281317 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:7:y:2024:i:2:p:83-93 Template-Type: ReDIF-Article 1.0 # input file: TJBA_A_2274088_J.xml processed with: repec_from_jats12.xsl darts-xml-transformations-20240209T083504 git hash: db97ba8e3a Author-Name: Dane Vanderkooi Author-X-Name-First: Dane Author-X-Name-Last: Vanderkooi Author-Name: Atefeh Mashatan Author-X-Name-First: Atefeh Author-X-Name-Last: Mashatan Author-Name: Ozgur Turetken Author-X-Name-First: Ozgur Author-X-Name-Last: Turetken Title: Introducing technological disruption: how breaking media attention on corporate events impacts online sentiment Abstract: One modern strategy to anticipate consumer reaction to new products and services involves looking towards social media sites to explore consumer opinions. A rich body of literature on social media marketing suggests that an effective way to leverage social media platforms is the empirical analysis of electronic word-of-mouth (eWOM), particularly through sentiment analysis (SA). We propose a novel method for innovators to leverage social media by exploring how breaking media attention on notable corporate events impacts the general public sentiment surrounding a pre-introduced, potentially disruptive innovation (PPDI). Twitter conversations surrounding Facebook’s pre-introduced payment system called Libra, a permissioned blockchain-based cryptocurrency, were analysed as a case study. The analysis suggests that breaking media attention leads to a significant change in sentiment polarity. An event with a preannouncement leads to an emotional momentum effect whereby sentiment polarity accumulates across an anticipation period. Implications for how managers may leverage these insights are discussed. Journal: Journal of Business Analytics Pages: 63-82 Issue: 2 Volume: 7 Year: 2024 Month: 04 X-DOI: 10.1080/2573234X.2023.2274088 File-URL: http://hdl.handle.net/10.1080/2573234X.2023.2274088 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:taf:tjbaxx:v:7:y:2024:i:2:p:63-82