TUILES: Tuesday Informal Lunchtime Seminars Fall 2016
Tuesday, September 20th
KMC 3-70
Lunch will be available at 12:15 pm. The seminar begins at 12:30 pm.
"Understanding the Effects of Recommender Systems on Consumer Views and Behaviors"
Gedas Adomavicius
Abstract: Interacting with online personalization and recommendation systems can have unintended effects on consumer preferences and economic behavior. In particular, consumers’ self-reported judgments can be significantly distorted by the system-predicted ratings that have been previously observed by consumers. This talk provides an overview of our recent stream of studies on this phenomenon. In particular, through laboratory experimentation, we find that personalized recommendations provided by an online system affects consumers’ ratings for products, even when the ratings are submitted immediately following consumption. We also find that recommendations displayed to participants significantly sway their willingness to pay for items in the direction of the recommendation. Furthermore, similar biases can be introduced not only via personalized, system-predicted ratings, but via non-personalized, aggregate user ratings as well. Our results show that, when shown separately, aggregate and personalized ratings create comparable effects on user preferences. However, when they are shown together, there is no cumulative increase in the effect, and personalized ratings tend to dominate the effect on user preferences. As recommender systems continue to become increasingly popular in today’s online environments, removing or mitigating such system-induced biases constitutes an important research problem. We further discuss user-interface-based approaches to proactively preventing biases before they occur, i.e., at rating collection time. We identify and report relative benefits and limitations of several user interface designs for recommender systems.
Short bio: Gedas Adomavicius is a professor in the Department of Information and Decision Sciences at the Carlson School of Management, University of Minnesota. He also holds the Carolyn I. Anderson Chair in Business Education Excellence. He received his PhD in computer science from New York University, and his general research interests revolve around computational techniques for aiding decision-making in information-intensive environments and include recommender systems, knowledge discovery and machine learning, and electronic market mechanisms. His research has been published in leading information systems and computer science journals, including "Information Systems Research", "Management Science", "Management Information Systems Quarterly", “Journal of Management Information Systems”, “INFORMS Journal on Computing”, "Journal of Operations Management", "IEEE Transactions on Knowledge and Data Engineering", "ACM Transactions on Information Systems", and "Data Mining and Knowledge Discovery". He received the U.S. National Science Foundation CAREER award for his research on personalization technologies as well as several other grants from various national funding agencies. He has served on several editorial boards of major journals, most recently as a Senior Editor of "Information Systems Research" (2012-2016).