How Does Competition Affect Exploration vs. Exploitation? A Tale of Two Recommendation Algorithms

60 Pages Posted: 24 Jan 2021 Last revised: 13 Dec 2022

See all articles by Huining Henry Cao

Huining Henry Cao

Cheung Kong Graduate School of Business

Liye Ma

University of Maryland - Department of Marketing

Z. Eddie Ning

University of British Columbia (UBC) - Sauder School of Business

Baohong Sun

Cheung Kong Graduate School of Business (New York); Cheung Kong Graduate School of Business (New York)

Date Written: December 12, 2022

Abstract

Through repeated interactions, firms today refine their understanding of individual users' preferences adaptively for personalization. In this paper, we use a continuous-time bandit model to analyze firms that recommend content to multi-homing consumers, a representative setting for strategic learning of consumer preferences to maximize lifetime value. In both monopoly and duopoly settings, we compare a forward-looking recommendation algorithm that balances exploration and exploitation to a myopic algorithm that only maximizes the quality of the next recommendation. Our analysis shows that compared to a monopoly, firms competing for users' attention focus more on exploitation than exploration. When users are impatient, competition decreases the return from developing a forward-looking algorithm. In contrast, development of a forward-looking algorithm may hurt users under monopoly but always benefits users under competition. Competing firms' decisions to invest in a forward-looking algorithm can create a prisoner's dilemma. Our results have implications for AI adoption as well as for policy makers on the effect of market power on innovation and consumer welfare.

Keywords: AI, multi-agent bandit, recommendation algorithm, innovation, competition, reinforcement learning, experimentation, CLV, value of learning, forward-looking optimization

JEL Classification: C73, D40, D83, L10, M31

Suggested Citation

Cao, Huining Henry and Ma, Liye and Ning, Z. Eddie and Sun, Baohong and Sun, Baohong, How Does Competition Affect Exploration vs. Exploitation? A Tale of Two Recommendation Algorithms (December 12, 2022). Available at SSRN: https://ssrn.com/abstract=3740164 or http://dx.doi.org/10.2139/ssrn.3740164

Huining Henry Cao

Cheung Kong Graduate School of Business ( email )

Oriental Plaza, Tower E3
One East Chang An Avenue
Beijing, 100738
China

Liye Ma

University of Maryland - Department of Marketing ( email )

College Park, MD 20742
United States
(301) 405-8982 (Phone)

Z. Eddie Ning (Contact Author)

University of British Columbia (UBC) - Sauder School of Business ( email )

2053 Main Mall
Vancouver, BC V6T 1Z2
Canada

Baohong Sun

Cheung Kong Graduate School of Business (New York) ( email )

230 Park Avenue
Suite 540
New York, NY 10169
United States

HOME PAGE: http://english.ckgsb.edu.cn/faculty/sun-baohong/

Cheung Kong Graduate School of Business (New York) ( email )

Oriental Plaza, Tower E3
One East Chang An Avenue
Beijing, 100738
China

HOME PAGE: http://english.ckgsb.edu.cn/faculty/sun-baohong/

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

Paper statistics

Downloads
280
Abstract Views
1,275
Rank
165,556
PlumX Metrics