Session-based Recommendations with Recurrent Neural Networks

TL;DR

This paper introduces an RNN-based method for session-based recommendations, demonstrating that modeling entire user sessions yields more accurate suggestions than traditional item-to-item approaches, especially with limited session data.

Contribution

The paper proposes a novel RNN approach with modifications like a ranking loss for session-based recommendations, outperforming existing methods on real datasets.

Findings

Marked improvements over traditional approaches

Effective modeling of user sessions with RNNs

Practical modifications enhance recommendation accuracy

Abstract

We apply recurrent neural networks (RNN) on a new domain, namely recommender systems. Real-life recommender systems often face the problem of having to base recommendations only on short session-based data (e.g. a small sportsware website) instead of long user histories (as in the case of Netflix). In this situation the frequently praised matrix factorization approaches are not accurate. This problem is usually overcome in practice by resorting to item-to-item recommendations, i.e. recommending similar items. We argue that by modeling the whole session, more accurate recommendations can be provided. We therefore propose an RNN-based approach for session-based recommendations. Our approach also considers practical aspects of the task and introduces several modifications to classic RNNs such as a ranking loss function that make it more viable for this specific problem. Experimental results on two data-sets show marked improvements over widely used approaches.