Moral Hazard and Transparency in Peer-to-Peer Auto Insurance with Telematics

2023 | International Conference on Information Systems | Citations: 0

Authors: Zhang, Yuxin; du, yalei; Zhang, Yuanyuan; Zhang, Quan

Abstract: Peer -to-peer (P2P) insurance uses new technology to connect policyholders and ... Expand

Abstract: Peer -to-peer (P2P) insurance uses new technology to connect policyholders and brings about disruptive innovation. While P2P insurance serving people with relatively high degrees of social connection, like friends and relatives, has been theoretically and practically underpinned, there is a lack of understanding about its viability or efficiency in serving strangers with few to no social ties as moral hazard may be substantial. In this paper, we bridge the gap by empirically measuring moral hazard in a P2P auto insurance where the insured individuals are strangers. Our research findings remove an obstacle that may hinder a broad application of the P2P insurance model among large groups of individuals. Moreover, we investigate factors that mitigate moral hazard and study the impact of transparency in premium balance on driving safety. We show that the transparency allows people to learn vicariously from peers' lessons and lets them drive more safely. Collapse

Topics: peer-to-peer model moral hazard price management business model mobile application

Methods: experimental group longitudinal research difference in differences causality analysis propensity score method

Exploiting Expert Knowledge for Assigning Firms to Industries: A Novel Deep Learning Method

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Zhao, Xiaohang; Fang, Xiao; He, Jing; Huang, Lihua

Abstract: Industry assignment, which assigns firms to industries according to a predefine ... Expand

Abstract: Industry assignment, which assigns firms to industries according to a predefined industry classification system (ICS), is fundamental to a large number of critical business practices, ranging from operations and strategic decision-making by firms to economic analyses by government agencies. Three types of expert knowledge are essential to effective industry assignment: definition-based knowledge (i.e., expert definitions of each industry), structure-based knowledge (i.e., structural relationships among industries as specified in an ICS), and assignment-based knowledge (i.e., prior firm-industry assignments performed by domain experts). Existing industry assignment methods utilize only assignment-based knowledge to learn a model that classifies unassigned firms to industries, overlooking definition-based and structurebased knowledge. Moreover, these methods only consider which industry a firm has been assigned to, ignoring the time-specificity of assignment-based knowledge, i.e., when the assignment occurs. To address the limitations of existing methods, we propose a novel deep learning-based method that not only seamlessly integrates the three types of knowledge for industry assignment but also takes the timespecificity of assignment-based knowledge into account. Methodologically, our method features two innovations: dynamic industry representation and hierarchical assignment. The former represents an industry as a sequence of time-specific vectors by integrating the three types of knowledge through our proposed temporal and spatial aggregation mechanisms. The latter takes industry and firm representations as inputs, computes the probability of assigning a firm to different industries, and assigns the firm to the industry with the highest probability. We conduct extensive evaluations with two widely used ICSs and demonstrate the superiority of our method over prevalent existing methods. Collapse

Topics: innovation management electronic finance industry 4.0 database system

Methods: support vector machine deep learning doc2vec experiment computational algorithm

Stigmergy in Open Collaboration: An Empirical Investigation Based on Wikipedia

2023 | Journal of Management Information Systems | Citations: 0

Authors: Zheng, Lei; Mai, Feng; Yan, Bei; Nickerson, Jeffrey V.

Abstract: Participants in open collaboration communities coproduce knowledge despite minim ... Expand

Abstract: Participants in open collaboration communities coproduce knowledge despite minimal explicit communication to coordinate the efforts. Studying how participants coordinate around the knowledge artifact and its impacts are critical for understanding the open knowledge production model. This study builds on the theory of stigmergy, wherein actions performed by a participant leave traces on a knowledge artifact and stimulate succeeding actions. We find that stigmergy involves two intertwined processes: collective modification and collective excitation. We propose a new measure of stigmergy based on the spatial and temporal clustering of contributions. By analyzing thousands of Wikipedia articles, we find that the degree of stigmergy is positively associated with community members' participation and the quality of the knowledge produced. This study contributes to the understanding of open collaboration by characterizing the spatial-temporal clustering of contributions and providing new insights into the relationship between stigmergy and knowledge production outcomes. These findings can help practitioners increase user engagement in knowledge production processes in order to create more sustainable open collaboration communities. Collapse

Topics: participatory design Wikipedia data quality electronic mail anonymity

Methods: design methodology cluster analysis literature sample robustness check instrumental variables estimation

Effect of a monetary incentive on responders’ empathy in online mental health platforms

2023 | International Conference on Information Systems | Citations: 0

Authors: Zhou, Junjie; Kishore, Rajiv; Lee, Michael

Abstract: ... Expand

Abstract: Collapse

Topics: online review

Methods: support vector machine longitudinal research machine learning robustness check supervised learning

Spoiled for Choice? Personalized Recommendation for Healthcare Decisions: A Multiarmed Bandit Approach

2023 | Information Systems Research | Citations: 3

Authors: Zhou, Tongxin; Wang, Yingfei; Yan, Lu (Lucy); Tan, Yong

Abstract: Online healthcare platforms provide users with various intervention programs to ... Expand

Abstract: Online healthcare platforms provide users with various intervention programs to promote personal wellness. Given the many options available, it’s often difficult for individuals to decide in which intervention to participate, especially when they lack the experience or knowledge to evaluate the interventions. This may discourage individuals’ continuous engagement in online health management. In this study, we are motivated to develop a personalized healthcare recommendation framework to help individuals better discover the interventions that fit their needs. Considering the challenges in intervention adaptation and diversification in a highly dynamic online healthcare environment, we propose an innovative online learning framework that synthesizes deep representation learning and a theory-guided diversity promotion scheme. We evaluate our approach through a real-world data set on users’ intervention participation in an online weight-loss community. Our results provide strong evidence for the effectiveness of our proposed recommendation framework and each of its design components. Our study contributes to the emerging information systems research on prescriptive analytics and the application of business intelligence. The proposed modeling framework and evaluation results offer important implications for multiple stakeholders, including online healthcare platforms, policymakers, and users. History: Ahmed Abbasi, Senior Editor; Huimin Zhao, Associate Editor. Funding: This work was supported in part by the National Natural Science Foundation of China [Grant 71729001]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2022.1191. Collapse

Topics: recommender system logistics management online learning system collaborative filtering usability

Methods: deep learning computational algorithm artificial neural network experiment design artifact

Theories: social cognitive theory

E-participation from the Perspective of ICT Adoption in Local Government Units: Drivers and Association with Sustainability

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Ziemba, Ewa; Grabara, Dariusz

Abstract: This research examines the ICT adoption drivers of e-participation and the asso ... Expand

Abstract: This research examines the ICT adoption drivers of e-participation and the association between e-participation and sustainability. A theoretical model of e-participation driven by ICT adoption in government units and associated with sustainability was proposed and verified among randomly selected 304 government units in Poland. It was revealed that e-participation is driven by ICT adoption in government units, particularly by thoughtful spending on ICT in government units, employees' ICT skills, managers' mastery, implementation of legal regulations on ICT usage, and front-office system security. Furthermore, a positive association between e-participation and sustainability was confirmed. Collapse

Topics: technology adoption IT skill government system IT security IS management

Methods: survey descriptive statistic chi squared test theoretical contribution correlation analysis

Best of Both Worlds: Combining Predictive Power with Interpretable and Explainable Results for Patient Pathway Prediction

2023 | European Conference On Information Systems | Citations: 0

Authors: Zilker, Sandra; Weinzierl, Sven; Zschech, Patrick; Kraus, Mathias; Matzner, Martin

Abstract: Proactively analyzing patient pathways can help healthcare providers to anticip ... Expand

Abstract: Proactively analyzing patient pathways can help healthcare providers to anticipate treatment-related risks, detect undesired outcomes, and allocate resources quickly. For this purpose, modern methods from the field of predictive business process monitoring can be applied to create data-driven models that capture patterns from past behavior to provide predictions about running process instances. Recent methods increasingly focus on deep neural networks (DNN) due to their superior prediction performances and their independence from process knowledge. However, DNNs generally have the disadvantage of showing black-box characteristics, which hampers dissemination in critical environments such as healthcare. To this end, we propose the design of HIXPred, a novel artifact combining predictive power with explainable results for patient pathway predictions. We instantiate HIXPred and apply it to a real-life healthcare use case for evaluation and demonstration purposes and conduct interviews with medical experts. Our results confirm high predictive performance while ensuring sufficient interpretability and explainability to provide comprehensible decision support.Keywords: Patient pathway prediction, predictive business process monitoring, explainable artificial intelligence, interpretable artificial intelligence, deep neural networks, business process management. Collapse

Topics: healthcare data shapley additive explanation explainable artificial intelligence business process management decision support

Methods: event log qualitative interview machine learning design artifact artificial neural network

Combined Digital Nudging to Leverage Public Transportation Use

2023 | European Conference On Information Systems | Citations: 0

Authors: Zimmermann, Sina; Feike, Paula; Hein, Andreas; Gewald, Heiko

Abstract: The urgency of global climate change is becoming increasingly evident, but prev ... Expand

Abstract: The urgency of global climate change is becoming increasingly evident, but prevailing mobility patterns in developed countries still cause severe environmental damage. Therefore, developed countries need to change their mobility patterns fundamentally, such as modal changes to public transportation instead of private car use. Digital nudging in digital mobility applications is a novel and promising way to influence modal changes to public transportation. In this study, we conduct an online experiment with 183 participants who are being nudged toward public transportation trip options. Our results show that combining two different digital nudges significantly affects the choice of public transportation options. By contrast, single nudges do not significantly change the choice of public transportation trips. With our findings, we contribute to the research stream of digital nudging and the transportation literature and provide insights for practice to address the adverse effects of current mobility patterns. Collapse

Topics: website mobile application web application Python logistics management

Methods: experimental group experiment regression analysis method survey literature study

When Do Evaluators Publicly Express Their Legitimacy Judgments? An Inquiry into the Role of Peer Endorsement and Evaluative Mode

2023 | Organization Science | Citations: 0

Authors: van den Broek, Tijs; Langley, David J.; Ehrenhard, Michel L.; Groen, Aard

Abstract: Legitimacy theory describes how individuals evaluate an organization’s behavior, ... Expand

Abstract: Legitimacy theory describes how individuals evaluate an organization’s behavior, form propriety evaluations, and subsequently decide whether to publicly express their legitimacy judgments. These individual judgments are influenced by sources of collective validity, for example, from recognized authority or from peer endorsement. Whereas most research on this topic has focused on the effects of authority, we study the influence of peer endorsement on the public expression of legitimacy judgments. Additionally, we assess evaluators’ preparedness to expend cognitive effort, that is, their evaluative mode, as an important condition under which judgment expressions are made. We present a set of three vignette experiments and one field study, all situated in social media that are quickly becoming the dominant setting for the expression of legitimacy judgments. This research provides new evidence that peer endorsement stimulates evaluators to express their judgments, particularly for evaluators who expend limited cognitive effort. Additionally, we find that evaluators in the active and passive evaluative modes act differently when their propriety evaluations are based on instrumental, moral, or relational considerations. These findings extend current legitimacy theory about how peer endorsement functions as a source of validity and when individual evaluators decide to publicly express their legitimacy judgments. This is important because individuals’ public expressions can bring about a cascade of judgments that change the consensus on an organization’s legitimacy, potentially contributing to institutional change.History: This paper has been accepted for the Organization Science Special Issue on Experiments in Organizational Theory.Supplemental Material: The online appendices are available at https://doi.org/10.1287/orsc.2022.1604. Collapse

Topics: website information privacy concern missing data social media privacy

Methods: experiment survey statistical power analysis field study theory development

Theories: organizational behavior theory media richness theory self categorization theory social identity theory

The Influence of Health Data on the Use of the Electronic Health Record (EHR) – a Mixed Methods Approach

2023 | Americas Conference on Information Systems | Citations: 0

Authors: von Kalckreuth, Niklas; Prümper, Alina; Feufel, Markus

Abstract: The use of electronic health records (EHRs) offers many benefits, but users are ... Expand

Abstract: The use of electronic health records (EHRs) offers many benefits, but users are also critical of them because of concerns about privacy and the sensitivity of health data. Given the ambiguity of data sensitivity, we examine which characteristics of health data influence users' upload behavior, and which are perceived as sensitive. A semi-structured interview (N=30) was conducted to locate characteristics of health data, which influence the user's upload behavior. These characteristics were then empirically evaluated in a user study (N=50). The complexity of diseases and their stigmatization potential are characteristics which influence the uploading behavior. We verify empirically that the uploading of health data is rejected when there is a high potential for stigmatization, while it is accepted when the complexity of the disease increases. Health data are considered by users to have different sensitivities, relative to stigmatization potential. Privacy Calculus regarding EHRs should consider these characteristics of health data. Collapse

Topics: healthcare data mobile application information privacy concern usage intention mobile health

Methods: experiment qualitative interview personal interview survey binomial logistic regression

Theories: privacy calculus theory