Learning Personalized Product Recommendations with Customer Disengagement

45 Pages Posted: 13 Sep 2018 Last revised: 25 Jun 2021

See all articles by Hamsa Bastani

Hamsa Bastani

University of Pennsylvania - The Wharton School

Pavithra Harsha

IBM Research

Georgia Perakis

Massachusetts Institute of Technology (MIT) - Sloan School of Management

Divya Singhvi

Massachusetts Institute of Technology (MIT) - Operations Research Center

Date Written: August 29, 2018

Abstract

Problem definition: We study personalized product recommendations on platforms when customers have unknown preferences. Importantly, customers may disengage when offered poor recommendations.

Academic / Practical Relevance: Online platforms often personalize product recommendations using bandit algorithms, which balance an exploration-exploitation tradeoff. However, customer disengagement—a salient feature of platforms in practice—introduces a novel challenge, since exploration may cause customers to abandon the platform. We propose a novel algorithm that constrains exploration to improve performance.

Methodology: We present evidence of customer disengagement using data from a major airline’s ad campaign; this motivates our model of disengagement, where a customer may abandon the platform when offered irrelevant recommendations. We formulate the customer preference learning problem as a linear bandit, with the notable difference that the customer’s horizon length is a function of past recommendations.

Results: We prove that no algorithm can keep all customers engaged. Unfortunately, classical bandit algorithms provably over-explore, causing every customer to eventually disengage. Motivated by the structural properties of the optimal policy in a scalar instance of our problem, we propose modifying bandit learning strategies by constraining the action space upfront using an integer program. We prove that this simple modification allows our algorithm to perform well by keeping a significant fraction of customers engaged.

Managerial Implications: Platforms should be careful to avoid over-exploration when learning customer preferences if customers have a high propensity for disengagement. Numerical experiments on movie recommendations data demonstrate that our algorithm can significantly improve customer engagement.

Keywords: bandits, recommendation systems, collaborative filtering, disengagement, cold start

Suggested Citation

Bastani, Hamsa and Harsha, Pavithra and Perakis, Georgia and Singhvi, Divya, Learning Personalized Product Recommendations with Customer Disengagement (August 29, 2018). Available at SSRN: https://ssrn.com/abstract=3240970 or http://dx.doi.org/10.2139/ssrn.3240970

Hamsa Bastani

University of Pennsylvania - The Wharton School ( email )

3641 Locust Walk
Philadelphia, PA 19104-6365
United States

Pavithra Harsha

IBM Research ( email )

T. J. Watson Research Center
Yorktown Heights, NY 10598
United States

Georgia Perakis

Massachusetts Institute of Technology (MIT) - Sloan School of Management ( email )

100 Main Street
E62-565
Cambridge, MA 02142
United States

Divya Singhvi (Contact Author)

Massachusetts Institute of Technology (MIT) - Operations Research Center ( email )

77 Massachusetts Avenue
Bldg. E 40-149
Cambridge, MA 02139
United States

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

Paper statistics

Downloads
258
Abstract Views
1,747
rank
148,820
PlumX Metrics