When and How to Diversify—A Multi-Category Utility Model for Personalized Content Recommendation

66 Pages Posted: 7 Dec 2016 Last revised: 20 May 2018

See all articles by Yicheng Song

Yicheng Song

University of Minnesota - Twin Cities - Carlson School of Management

Nachiketa Sahoo

Boston University - Questrom School of Business

Elie Ofek

Harvard Business School - Marketing Unit

Date Written: August 31, 2016

Abstract

Sometimes we desire change, a break from the same, or an opportunity to fulfill different aspects of our needs. Noting that consumers seek variety, several approaches have been developed to diversify items recommended by personalized recommender systems. However, current diversification strategies operate under a one-shot paradigm-without considering the evolution of preferences due to recent consumption. Therefore, such methods often sacrifice accuracy. In the context of online media consumption, we show that by recognizing that consumption in a session is the result of a sequence of utility maximizing selections from various categories, one can increase recommendation accuracy by dynamically tailoring the diversity of suggested items to the diversity sought by the consumer. Our approach is based on a multi-category utility model that captures a consumer's preference for different categories of content, how quickly she satiates with one category and wishes to substitute it with another, and how she trades off her own costly search efforts with selecting from a recommended list to discover new content. Taken together, these three elements allow us to characterize how an individual selects a diverse set of items to consume over the course of a session, and how likely she is to click on content recommended to her. We estimate the model using a clickstream dataset from a large media outlet and apply it to determine the most relevant content to recommend at different stages of an online session. We find that our approach generates recommendations that are on average about 10% more accurate than optimized alternatives and about 25% more accurate than those diversified using existing diversification strategies. Moreover, the proposed method recommends content with diversity that more closely matches the diversity sought by readers-exhibiting the lowest concentration-diversification bias when compared to other personalized recommender systems. Using a policy simulation, we estimate that recommending content using the proposed approach would result in visitors reading 23% additional articles at the studied website and deriving 35% higher utility. This could lead to immediate gain in revenue for the publisher and longer-term improvements in customer satisfaction and retention at the site.

Keywords: Recommender Systems, Personalization, Recommendation Diversity, Variety Seeking, Collaborative Filters, Consumer Utility Models, Content Consumption, Digital Media, Clickstream Analysis, Learning-to-Rank

Suggested Citation

Song, Yicheng and Sahoo, Nachiketa and Ofek, Elie, When and How to Diversify—A Multi-Category Utility Model for Personalized Content Recommendation (August 31, 2016). Boston University Questrom School of Business Research Paper No. 2880779, Available at SSRN: https://ssrn.com/abstract=2880779 or http://dx.doi.org/10.2139/ssrn.2880779

Yicheng Song

University of Minnesota - Twin Cities - Carlson School of Management ( email )

19th Avenue South
Minneapolis, MN 55455
United States

HOME PAGE: http://people.bu.edu/ycsong/

Nachiketa Sahoo (Contact Author)

Boston University - Questrom School of Business ( email )

595 Commonwealth Avenue
Boston, MA MA 02215
United States

HOME PAGE: http://people.bu.edu/nachi/

Elie Ofek

Harvard Business School - Marketing Unit ( email )

Soldiers Field
Boston, MA 02163
United States
617-495-6301 (Phone)
617-496-5853 (Fax)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
263
Abstract Views
1,562
rank
136,469
PlumX Metrics