Optimizing recommendations under abandonment risks: Models and algorithms

Abstract

User abandonment behaviors are quite common in recommendation applications such as online shopping recommendation and news recommendation. To maximize its total “reward” under the risk of user abandonment, the online platform needs to carefully optimize its recommendations for its users. Because inappropriate recommendations can lead to user abandoning the platform, which results in a short learning duration and reduces the cumulative reward. To address this problem, we formulate a new online decision model and propose an algorithmic framework to transfer similar users’ information via parametric estimation, and employ this knowledge to optimize later decisions. The framework’s theoretical guarantees depend on requirements for its transfer learning oracle and online decision oracle. We then design an online learning algorithm consisting of two components that fulfills each corresponding oracle’s requirements. We also conduct extensive experiments to demonstrate our algorithm’s performance.