STAR: A Session-Based Time-Aware Recommender System

TL;DR

The paper introduces STAR, a session-based recommender system that leverages temporal information within sessions to improve prediction accuracy, outperforming existing models on key metrics.

Contribution

STAR is the first to incorporate continuous time intervals between events into session representations without discretization, enhancing recommendation performance.

Findings

STAR outperforms baseline models in Recall and MRR.

Utilizing temporal intervals improves session representation quality.

Continuous time embedding benefits recommendation accuracy.

Abstract

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. Our mechanism revises session representation by embedding time intervals without employing discretization. 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.