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

TL;DR

This paper introduces PASRec, a diffusion-based framework for active sequential recommendation that jointly models the timing of user interactions and the content of recommended items, improving prediction accuracy.

Contribution

It presents a novel joint modeling approach for timing and content in active recommendation, addressing the challenge of estimating interaction timing and generating relevant items.

Findings

PASRec outperforms eight state-of-the-art baselines on five benchmark datasets.

Joint modeling of timing and content improves recommendation accuracy.

The framework effectively predicts both when and what to recommend.

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.