Optimal Set Recommendations Based on Regret

Current conversational recommender systems do not offer guarantees on the quality of their recommendations, either because they do not maintain a model of a user’s utility function, or do so in an ad hoc fashion. In this paper, we propose an approach to recommender systems that incorporates explicit utility models into the recommendation process in a decision-theoretically sound fashion. The system maintains explicit constraints on the user’s utility based on the semantics of the preferences revealed by the user’s actions. In particular, we propose and investigate a new decision criterion, setwise maximum regret, for constructing optimal recommendation sets. This new criterion extends the mathematical notion of maximum regret used in decision theory and preference elicitation to sets. We develop computational procedures for computing setwise max regret. We also show that the criterion suggests choice sets for queries that are myopically optimal: that is, it refines knowledge of a user’s utility function in a way that reduces max regret more quickly than any other choice set. Thus setwise max regret acts both as guarantee on the quality of our recommendations and as a driver for further utility elicitation. Our simulation results suggest that this utilitytheoretically sound approach to user modeling allows much more effective navigation of a product space than traditional approaches based on, for example, heuristic utility models and product similarity measures.