STAR: A Session-Based Time-Aware Recommender System

Session-Based Recommenders (SBRs) aim to predict users' next preferences regard to their previous interactions in sessions while there is no historical information about them. Modern SBRs utilize deep neural networks to map users' current interest(s) during an ongoing session to a latent space so that their next preference can be predicted. Although state-of-art SBR models achieve satisfactory results, most focus on studying the sequence of events inside sessions while ignoring temporal details of those events. In this paper, we examine the potential of session temporal information in enhancing the performance of SBRs, conceivably by reflecting the momentary interests of anonymous users or their mindset shifts during sessions. We propose the STAR framework, which utilizes the time intervals between events within sessions to construct more informative representations for items and sessions. Empirical results on Yoochoose and Diginetica datasets show that the suggested method outperforms the state-of-the-art baseline models in Recall and MRR criteria. A Session-based recommender system aims to predict the users' next item based on their previous interacted items in sessions. Such a system has two characteristics that distinguish it from other recommender systems: 1) The lack of users' identity information and 2) the significance of short-term preferences Wang et al. (2019). Since the only information source is the interaction data in an ongoing session, SBRs suffer from users' identity unavailability.