Hierarchical Context-Aware Recurrent Network for Session-Based Recommendation

Abstract

Recently, session-based recommendations are becoming popular to explore the temporal characteristics of customers' interactive behaviors. The user's behavior in the session not only contains the item sequence but also rich context information such as how the user navigates to the item, the operation type, and the dwell time on the item, which may impact users' next actions. How to incorporate these contextual features effectively for session-based recommendations remains a great challenge. In this paper, we divide them into two hierarchies: session-context at the macro-level and event-context at the micro-level, and then propose a Hierarchical Context-aware Recurrent Network (HiCAR) by incorporating both users' micro-interaction with the item and the two-hierarchy contexts, wherein a Session Context Learning module with the n-way hybrid strategy is adopted to model multi-feature interactions in the session-context. Moreover, an Event Context Learning module consists of TIME-LSTM with a time gate is designed to model the sequential behavior with event-context. By experimenting on two real-world datasets, we find that our HiCAR model outperforms state-of-the-art baselines on both datasets, which demonstrates its advantages in modeling users' sequential behaviors and contexts simultaneously.