Modeling User Retention through Generative Flow Networks

Abstract

Recommender systems aim to fulfill the user's daily demands. While most existing research focuses on maximizing the user's engagement with the system, it has recently been pointed out that how frequently the users come back for the service also reflects the quality and stability of recommendations. However, optimizing this user retention behavior is non-trivial and poses several challenges including the intractable leave-and-return user activities, the sparse and delayed signal, and the uncertain relations between users' retention and their immediate feedback towards each item in the recommendation list. In this work, we regard the retention signal as an overall estimation of the user's end-of-session satisfaction and propose to estimate this signal through a probabilistic flow. This flow-based modeling technique can back-propagate the retention reward towards each recommended item in the user session, and we show that the flow combined with traditional learning-to-rank objectives eventually optimizes a non-discounted cumulative reward for both immediate user feedback and user retention. We verify the effectiveness of our method through both offline empirical studies on two public datasets and online A/B tests in an industrial platform.

KDD-ADS 2024

References in corpus (11)

• Deep Reinforcement Learning for Page-wise Recommendations
• Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning
• AutoMLP: Automated MLP for Sequential Recommendations
• Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems
• Whole-Chain Recommendations
• Exploration and Regularization of the Latent Action Space in Recommendation
• User Retention-oriented Recommendation with Decision Transformer
• Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
• Generative Flow Network for Listwise Recommendation
• KuaiSim: A Comprehensive Simulator for Recommender Systems
• AutoAssign+: Automatic Shared Embedding Assignment in Streaming Recommendation

Cited by in corpus (1)

• Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems