Fast Generation of Heterogeneous Mental Models from Longitudinal Data by Combining Genetic Algorithms and Fuzzy Cognitive Maps

2023 | HICSS | Citations: 0

Authors: Bernard, D.; Cussat-Blanc, S.; Giabbanelli, P.

Abstract: Models that capture the heterogeneous perspectives of individuals are essential ... Expand

Abstract: Models that capture the heterogeneous perspectives of individuals are essential to test tailored interventions, such as behavior change interventions. Although Fuzzy Cognitive Maps (FCMs) have a rich history in depicting systems, they were either developed at an individual level through facilitated sessions, or created for an entire population through machine learning. The need to automatically create individual FCMs from data has started to be addressed, but the proposed solution was computationally prohibitive and thus could not be deployed over a large population. In this work, we use a state-of-the-art evolutionary algorithm (CMA-ES) to create individual FCMs by leveraging the growing availability of longitudinal data. We demonstrate on a real-world case study that our solution is both accurate and fast to compute. Our experiments on synthetic data also show that our approach can scale to a large number of measurements, but it cannot currently be applied to highly noisy datasets. Collapse

Topics: Python

Methods: computational algorithm case study simulation longitudinal research descriptive statistic

Factors that Affect Consumer-to-Consumer Sales: An Inductive Predictive Analytics Approach

2023 | Americas Conference on Information Systems | Citations: 0

Authors: El Arabaty, Ashraf; Okoli, Chitu

Abstract: This study investigates factors affecting consumer-to-consumer (C2C) sales perf ... Expand

Abstract: This study investigates factors affecting consumer-to-consumer (C2C) sales performance, specifically in the context of second-hand luxury goods. Using a large dataset of users from a French C2C luxury fashion website, the research identifies factors influencing C2C sales beyond current knowledge. Findings show that the number of followers a seller has, as well as the number of products a seller wishes for and likes, are associated with increased sales. Additionally, the study uncovers unexpected results: sellers listing many products also buy many products, and the number of users a seller follows is associated with increased sales. These findings contribute to a better understanding of the unique characteristics of C2C e-commerce. The article provides practical implications for sellers and C2C platforms to improve their sales performance, catering to the dual-role nature of users in C2C transactions. Collapse

Topics: electronic commerce website explainable artificial intelligence social capital

Methods: machine learning linear regression analysis literature study random forest classification decision tree classification

Rejoinder to Comments on Recent Developments in PLS

2023 | Communications of the Association for Information Systems | Citations: 0

Authors: Evermann, Jöerg; Rönkkö, Mikko

Abstract: When we were first invited to write an essay on the use of PLS for CAIS, we wan ... Expand

Abstract: When we were first invited to write an essay on the use of PLS for CAIS, we wanted to focus on recent developments to help applied IS researchers, and the CAIS community of authors, reviewers, and editors make use of the latest research on and methodological advances in PLS. Recognizing that Information Systems is arguably the discipline in which the use of PLS as an alternative to CB-SEM originated and is most widely used, we realized that, pragmatically, our essay must focus on how to use PLS, not whether to use PLS.We received six interesting responses from researchers active in the PLS community. Their thoughts on our presentation of recent developments in PLS show very different perspectives with many points of difference amongst points of agreement in all the responses. In this rejoinder, we briefly respond to the received comments, clarify our position and ideas, and identify points of agreement (and disagreement). We emphasize that none of the responses give us cause to revise or eliminate our recommendations in recent developments.Overall, we believe this discussion on PLS to be valuable in advancing the use of PLS in Information Systems, which is, as we show in this rejoinder, an urgent issue. Collapse

Topics: spreadsheet marketing management Pandora website digital service

Methods: partial least squares regression structural equation modeling simulation consistent partial least squares path modeling PLS tool

Theories: unified theory of acceptance and use of technology

Near-Infrared Spectroscopy for Bladder Monitoring: A Machine Learning Approach

2023 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Fechner, Pascal; König, Fabian; Kratsch, Wolfgang; Lockl, Jannik; Röglinger, Maximilian

Abstract: Patients living with neurogenic bladder dysfunction can lose the sensation of th ... Expand

Abstract: Patients living with neurogenic bladder dysfunction can lose the sensation of their bladder filling. To avoid over-distension of the urinary bladder and prevent long-term damage to the urinary tract, the gold standard treatment is clean intermittent catheterization at predefined time intervals. However, the emptying schedule does not consider actual bladder volume, meaning that catheterization is performed more often than necessary, which can lead to complications such as urinary tract infections. Time-consuming catheterization also interferes with patients' daily routines and, in the case of an empty bladder, uses human and material resources unnecessarily. To enable individually tailored and volume-responsive bladder management, we design a model for the continuous monitoring of bladder volume. During our design science research process, we evaluate the model's applicability and usefulness through interviews with affected patients, prototyping, and application to a real-world in vivo dataset. The developed prototype predicts bladder volume based on relevant sensor data (i.e., near-infrared spectroscopy and acceleration) and the time elapsed since the previous micturition. Our comparison of several supervised state-of-the-art machine and deep learning models reveals that a long short-term memory network architecture achieves a mean absolute error of 116.7 ml that can improve bladder management for patients. Collapse

Topics: computer hardware open source mobile application user interface programming language

Methods: design artifact qualitative interview design process support vector machine computational algorithm

Addressing Learners' Heterogeneity in Higher Education: An Explainable AI-based Feedback Artifact for Digital Learning Environments

2023 | International Conference on Business Informatics | Citations: 0

Authors: Haag, Felix; Günther, Sebastian A.; Hopf, Konstantin; Handschuh, Philipp; Klose, Maria; Staake, Thorsten

Abstract: ... Expand

Abstract: Collapse

Topics: explainable artificial intelligence online learning system analytical information system project management IT project management

Methods: design science survey design principle design artifact two sample t-test with equal variance

A Collective Opinion Mechanism for Crowdfunding Recommendation

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Jin, Bih-Huang; Li, Yung-Ming; Kamolporn, Sanamlao

Abstract: ... Expand

Abstract: Collapse

Topics: crowdsourcing crowdfunding Twitter social network Python

Methods: sentiment analysis experiment topic model logistic regression parametric test

Diffusion of real versus misinformation during a crisis event: A big data-driven approach

2023 | International Journal of Information Management | Citations: 0

Authors: King, Kelvin K.; Wang, Bin

Abstract: Misinformation has captured the interest of academia in recent years with severa ... Expand

Abstract: Misinformation has captured the interest of academia in recent years with several studies looking at the topic broadly with inconsistent results. In this research, we attempt to bridge the gap in the literature by examining the impacts of user-, time-, and content-based characteristics that affect the virality of real versus misinformation during a crisis event. Using a big data-driven approach, we collected over 42 million tweets during Hurricane Harvey and obtained 3589 original verified real or false tweets by cross-checking with fact-checking websites and a relevant federal agency. Our results show that virality is higher for misinformation, novel tweets, and tweets with negative sentiment or lower lexical density. In addition, we reveal the opposite impacts of sentiment on the virality of real news versus misinformation. We also find that tweets on the environment are less likely to go viral than the baseline religious news, while real social news tweets are more likely to go viral than misin­ formation on social news. Collapse

Topics: Twitter misinformation social media hurricane big data

Methods: machine learning computational algorithm natural language processing decision tree classification gradient boosting

Tackling the Accuracy-Interpretability Trade-off: Interpretable Deep Learning Models for Satellite Image-based Real Estate Appraisal

2023 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Kucklick, Jan-Peter; Müller, Oliver

Abstract: Deep learning models fuel many modern decision support systems, because they typ ... Expand

Abstract: Deep learning models fuel many modern decision support systems, because they typically provide high predictive performance. Among other domains, deep learning is used in real-estate appraisal, where it allows extending the analysis from hard facts only (e.g., size, age) to also consider more implicit information about the location or appearance of houses in the form of image data. However, one downside of deep learning models is their intransparent mechanic of decision making, which leads to a trade-off between accuracy and interpretability. This limits their applicability for tasks where a justification of the decision is necessary. Therefore, in this article, we first combine different perspectives on interpretability into a multi-dimensional framework for a socio-technical perspective on explainable artificial intelligence. Second, we measure the performance gains of using multi-view deep learning, which leverages additional image data (satellite images) for real estate appraisal. Third, we propose and test a novel post hoc explainability method called Grad-Ram. This modified version of Grad-Cam mitigates the intransparency of convolutional neural networks for predicting continuous outcome variables. With this, we try to reduce the accuracy-interpretability trade-off of multi-view deep learning models. Our proposed network architecture outperforms traditional hedonic regression models by 34% in terms of MAE. Furthermore, we find that the used satellite images are the second most important predictor after square feet in our model and that the network learns interpretable patterns about the neighborhood structure and density. Collapse

Topics: Bing explainable artificial intelligence shapley additive explanation video conference price management

Methods: principal component analysis data transformation experiment artificial neural network regression analysis method

Theories: game theory

Between Attention and Portfolio Adjustment: Insights from Machine Learning-based Risk Preference Assessment

2023 | International Conference on Information Systems | Citations: 0

Authors: Li, Xin; Rai, Arun; Song, Qingping; Xu, Sean Xin

Abstract: Financial firms recommend products to customers, intending to gain their attent ... Expand

Abstract: Financial firms recommend products to customers, intending to gain their attention and change their portfolios. Based on behavioral decision-making theory, we argue attention's effect on portfolio adjustment is through the risk deviation between portfolio risk and their risk preference. Thus, to fully understand the adjustment process, it is necessary to assess customers' risk preferences. In this study, we use machine learning methods to measure customers' risk preferences. Then, we build a dynamic adjustment model and find that attention's impact on portfolio adjustment speed is stronger when customers' risk preference is higher than portfolio risk (which needs an upward adjustment) and when customers' risk preference is within historical portfolio risk experience. We conducted a field experiment and found that directing customers' attention to products addressing the risk deviation would lead to more portfolio adjustment activities. Our study illustrates the role of machine learning in enhancing our understanding of financial decision-making. Collapse

Topics: decision making analytical information system electronic finance web page online banking

Methods: field experiment experimental group machine learning XGBoost digital trace data

A two-stage prediction model based on behavior mining in livestream e-commerce

2023 | Decision Support Systems | Citations: 0

Authors: Lin, Qinping; Jia, Ning; Chen, Liao; Zhong, Shiquan; Yang, Yuance; Gao, Tong

Abstract: Livestream e-commerce has been developing at a tremendous pace in recent years. ... Expand

Abstract: Livestream e-commerce has been developing at a tremendous pace in recent years. On livestream platforms, such as Douyin, a retailer attracts viewers into the live room through short video advertising, and then streamers promote and sell products in real time. In such a scenario, an accurate prediction of traffic and sales plays an essential role in operation management, including live content strategy and inventory control. However, complex behaviors (follow, share, comment, etc.) of users and long conversion paths (from seeing the advertisement to entering the live room, and to purchasing the goods) lead to poor performance of traditional prediction methods. Additionally, few studies focus on advertising information in evaluating live room performance. Therefore, we propose a two-stage learning model for traffic and sales prediction based on behavior mining, which combines marketing models and deep learning methods. In the first stage, we integrate user behaviors before getting into the live room with short video advertising data for traffic prediction. In the second stage, based on the traditional marketing model, AIDA (Attention-Interest-Desire-Action), we design a funnel convolutional neural network (FCNN) to learn sophisticated behaviors in the live room in both time and behavior orientations, and take the predicted traffic volume as the auxiliary information for sales prediction. Extensive experiments on real-world datasets from Douyin illustrate the efficacy of our proposed method, which shows the value of fusing marketing models with deep learning techniques. Furthermore, the in-depth analysis provides practical insights into user behaviors for livestream e-commerce. Collapse

Topics: electronic commerce advertising management user behavior marketing management personality

Methods: experiment deep learning time series analysis longitudinal research convolutional neural network

Theories: management theory