Sequential Relevance Maximization with Binary Feedback

TL;DR

This paper studies a sequential recommendation problem with binary user feedback, aiming to optimize relevance while learning user preferences, and proposes algorithms with provable performance guarantees.

Contribution

It characterizes the optimal policy structure and introduces heuristic algorithms with strong theoretical performance bounds for relevance maximization.

Findings

Heuristic policies perform close to optimal in simulations.

The optimal policy has specific structural properties.

Proposed algorithms balance exploration and exploitation effectively.

Abstract

Motivated by online settings where users can provide explicit feedback about the relevance of products that are sequentially presented to them, we look at the recommendation process as a problem of dynamically optimizing this relevance feedback. Such an algorithm optimizes the fine tradeoff between presenting the products that are most likely to be relevant, and learning the preferences of the user so that more relevant recommendations can be made in the future. We assume a standard predictive model inspired by collaborative filtering, in which a user is sampled from a distribution over a set of possible types. For every product category, each type has an associated relevance feedback that is assumed to be binary: the category is either relevant or irrelevant. Assuming that the user stays for each additional recommendation opportunity with probability $\beta$ independent of the past, the problem is to find a policy that maximizes the expected number of recommendations that are deemed relevant in a session. We analyze this problem and prove key structural properties of the optimal policy. Based on these properties, we first present an algorithm that strikes a balance between recursion and dynamic programming to compute this policy. We further propose and analyze two heuristic policies: a `farsighted' greedy policy that attains at least $1-\beta$ factor of the optimal payoff, and a naive greedy policy that attains at least $\frac{1-\beta}{1+\beta}$ factor of the optimal payoff in the worst case. Extensive simulations show that these heuristics are very close to optimal in practice.