When and What to Recommend: Joint Modeling of Timing and Content for Active Sequential Recommendation

2025-11-23

AI Summary

This paper addresses the problem of proactive sequential recommendation after user application termination, jointly predicting the Time of Interest (ToI) and the corresponding Item of Interest (IoI). To this end, we propose PASRec—the first framework to integrate diffusion models into sequential recommendation—featuring a conditional, time-aware generative mechanism that enables end-to-end joint modeling of ToI and IoI. Our method synergistically combines temporal dynamics modeling with fine-grained conditional content generation, thereby significantly improving both timeliness and relevance of recommendations. Extensive experiments across five benchmark datasets under two evaluation protocols—leave-one-out and time-based splitting—demonstrate that PASRec consistently outperforms eight state-of-the-art baselines. These results validate the effectiveness and superiority of the diffusion-based generative paradigm for proactive recommendation.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Time-Series/Data Streams
• Computer Vision: Diffusion Models for Vision

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Content-based information diffusion
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Sequential recommendation models user preferences to predict the next target item. Most existing work is passive, where the system responds only when users open the application, missing chances after closure. We investigate active recommendation, which predicts the next interaction time and actively delivers items. Two challenges: accurately estimating the Time of Interest (ToI) and generating Item of Interest (IoI) conditioned on the predicted ToI. We propose PASRec, a diffusion-based framework that aligns ToI and IoI via a joint objective. Experiments on five benchmarks show superiority over eight state-of-the-art baselines under leave-one-out and temporal splits.

Problem

• Predicting optimal timing for active item recommendations to users
• Generating relevant content recommendations based on predicted timing
• Jointly modeling user interaction timing and item preference dynamics

Innovation

• Active recommendation predicts next interaction timing
• Diffusion-based framework jointly models time and content
• Aligns Time of Interest with Item of Interest