• Home
  • Introduction
  • Faculty Directory
  • Seminar
  • Contact Us
  • Peking University
  • Belt & Road Institute
  • 中文
  • Seminar

    speaker Zhiqiang (Eric) Zheng, University of Texas at Dallas time Monday, June 24th , 09:00-10:30
    place Room 217, Guanghua Building 2

    Management Science and Information Systems' Seminar2019-14

    Title: Detecting and Deterring Online Customer Misbehavior
    Speaker: Zhiqiang (Eric) Zheng, University of Texas at Dallas

    Time:  Monday, June 24th ,  09:00-10:30

    Location: Room 217, Guanghua Building 2


    Customer misbehavior  in firms’social media presents a serious challenge to businesses. This  paper develops an algorithmic approach to detect and restrain online  customer misbehavior. Specifically, we build on natural language  processing and deep learning techniques to automatically detect customer  misbehaviors by mining a firm’s social media data, and then implement  two norm enforcement mechanisms– punishment and common identity –to  restrain customer misbehavior without compromising customer  relationship. In collaboration with a prominent apparel e-commerce  company, we conducted a field experiment based on the unique data  provided by the firm. The results show that our algorithmic solution  achieves excellent performance in detecting customer misbehavior,  improving detection performance by 7 to 9 percent on average. The  results from the field experiment indicate that punishment reduces  customer misbehavior considerably in the short term, but this effect  decays over time; whereas common identity has an initially small but  persistent effect on misbehavior reduction in the long run. Importantly,  we show that the combination of punishment and common identity can  achieve a more substantial and longer-term reduction. In addition, we  find that punishing dysfunctional customers decreases their purchase  frequency, whereas imposing a common identity on those customers  improves their purchase behavior. Interestingly, our results show that  combining the two enforcement mechanisms offers an effective control  strategy to alleviate the detrimental effect of punishment. Finally, we  reveal the heterogeneous treatment effect on customers ranging from  novice to experienced ones.


    Zhiqiang (Eric) Zheng is  the Ashbel Smith Professor of Information Systems with a joint  appointment in Finance at the Jindal School of Management, University of  Texas at Dallas. He received his PhD from the Wharton School of  Business, University of Pennsylvania. His current research interests  focus on financial technology, Blockchain analytics and healthcare  analytics. His papers have appeared in journals such as Information  Systems Research, Management Science, MIS Quarterly, and Production and  Operations Management. He currently serves as a senior editor for  Information Systems Research and is the editor for the Fintech and  Blockchain special issue.

    Your participation is warmly welcomed!

    © 2019 Guanghua School of Management Peking University