Thompson Sampling for a Fatigue-aware Online Recommendation System

원문 초록

In this paper we consider an online recommendation setting, where a platform recommends a sequence of items to its users at every time period. The users respond by selecting one of the items recommended or abandon the platform due to fatigue from seeing less useful items. Assuming a parametric stochastic model of user behavior, which captures positional effects of these items as well as the abandoning behavior of users, the platform's goal is to recommend sequences of items that are competitive to the single best sequence of items in hindsight, without knowing the true user model a priori. Naively applying a stochastic bandit algorithm in this setting leads to an exponential dependence on the number of items. We propose a new Thompson sampling based algorithm with expected regret that is polynomial in the number of items in this combinatorial setting, and performs extremely well in practice.