Learning with Abandonment
This addresses the challenge of balancing personalization and user retention for platforms, but it appears incremental as it builds on existing learning models with a specific risk consideration.
The paper tackles the problem of a platform learning personalized policies for users while facing the risk of user abandonment due to dissatisfaction, proposing a thresholded learning model and analyzing optimal policies and performance guarantees.
Consider a platform that wants to learn a personalized policy for each user, but the platform faces the risk of a user abandoning the platform if she is dissatisfied with the actions of the platform. For example, a platform is interested in personalizing the number of newsletters it sends, but faces the risk that the user unsubscribes forever. We propose a general thresholded learning model for scenarios like this, and discuss the structure of optimal policies. We describe salient features of optimal personalization algorithms and how feedback the platform receives impacts the results. Furthermore, we investigate how the platform can efficiently learn the heterogeneity across users by interacting with a population and provide performance guarantees.