The Schwartz Reisman weekly seminar series welcomes Shreyas Sekar, assistant professor of operations management at the University of Toronto with joint appointments at the Rotman School of Management and the Department of Management, UTSC. Prior to this, he was a postdoctoral fellow at the Harvard Business School’s Laboratory for Innovation Science. Currently, Sekar’s research is centered around the economics of information on online platforms and decision making in strategic environments.
Talk title
“Learning product rankings in online retail: Diversity, robustness, and manipulation”
Abstract
Online retailer platforms such as Amazon and Wayfair increasingly leverage information as a tool to influence consumers. In particular, given short attention spans on the web, controlling “how information is presented to customers” can significantly impact their purchase decisions. This talk focuses on a crucial problem faced by e-commerce platforms, namely ranking an assortment of products, i.e., the order in which products are presented to users.
Motivated by the prevalence of special events (e.g., Christmas sales, flash sales), I first look at the product ranking problem in dynamic and uncertain environments, where customers’ preferences and attention spans are unknown to the retailer. In such scenarios, commonly used policies—e.g., ranking products by popularity—lead to poor outcomes as they do not take advantage of the heterogeneity in customer preferences. Instead, I present a new online learning algorithm that balances popularity with diversity and converges to a near-optimal ranking by learning from customers’ clickstream data. Empirically testing this new learning policy on clickstream data from Wayfair.com shows that the proposed algorithm yields a significant increase (5-30%) in customer engagement, measured via click-based metrics.
In the final part of this talk, I discuss another major threat to the smooth operation of such platforms, namely manipulation in the form of click fraud or fake reviews. I argue that even a small amount of fraudulent behaviour can completely derail any data-driven algorithm adopted by retailers. I conclude by briefly touching upon results from recent work on how to make learning algorithms robust to manipulation even when we are completely oblivious to the number and identity of fake users. Overall, this talk will provide a number of broad insights on how online platforms can balance popularity and diversity in their rankings and be resilient against the actions of clickfarms.
Recommended readings
K. Ferreira, S. Parthasarathy, S. Sekar, “Learning to Rank and Assortment of Products” (2020).
N. Golrezaei, V. Manshadi, J. Schneider, S. Sekar, “Learning Product Rankings Robust to Fake Users” (2020).
About Shreyas Sekar
Shreyas Sekar is an assistant professor of operations management at the University of Toronto with joint appointments at the Rotman School of Management and the Department of Management, UTSC. Prior to this, he was a postdoctoral fellow at the Harvard Business School’s Laboratory for Innovation Science. Currently, Sekar’s research is centered around the economics of information on online platforms and decision making in strategic environments. He completed his PhD in computer science at the Rensselaer Polytechnic Institute, in New York. Sekar was awarded the Robert McNaughton Prize for the best graduate dissertation in CS for his work on non-discriminative algorithmic pricing.
About the SRI Seminar Series
The SRI Seminar Series brings together the Schwartz Reisman community and beyond for a robust exchange of ideas that advance scholarship at the intersection of technology and society. Seminars are led by a leading or emerging scholar and feature extensive discussion.
Each week, a featured speaker will present for 45 minutes, followed by 45 minutes of discussion. Registered attendees will be emailed a Zoom link approximately one hour before the event begins. The event will be recorded and posted online.
Shreyas Sekar