Top-Personalized-K Recommendation

Abstract

The conventional top-K recommendation, which presents the top-K items with the highest ranking scores, is a common practice for generating personalized ranking lists. However, is this fixed-size top-𝐾 recommendation the optimal approach for every user's satisfaction? Not necessarily. We point out that providing fixed-size recommendations without taking into account user utility can be suboptimal, as it may unavoidably include irrelevant items or limit the exposure to relevant ones. To address this issue, we introduce Top-Personalized-𝐾 Recommendation, a new recommendation task aimed at generating a personalized-sized ranking list to maximize individual user satisfaction. As a solution to the proposed task, we develop a model-agnostic framework named PerK. PerK estimates the expected user utility by leveraging calibrated interaction probabilities, subsequently selecting the recommendation size that maximizes this expected utility. Through extensive experiments on real-world datasets, we demonstrate the superiority of PerK in Top-Personalized-𝐾 recommendation task. We expect that Top-Personalized-𝐾 recommendation has the potential to offer enhanced solutions for various real-world recommendation scenarios, based on its great compatibility with existing models.