Metric Learning for Session-based Recommendations

TL;DR

This paper introduces a metric learning approach for session-based recommendations, creating a shared embedding space for sessions and items to improve prediction accuracy with simpler models.

Contribution

It proposes a novel metric learning framework for session-based recommendation systems that outperforms existing methods with less complex architectures.

Findings

Metric learning outperforms traditional ranking methods on four datasets.

Simple architectures are sufficient to achieve state-of-the-art results.

Ablation studies highlight the effectiveness of the proposed approach.

Abstract

Session-based recommenders, used for making predictions out of users' uninterrupted sequences of actions, are attractive for many applications. Here, for this task we propose using metric learning, where a common embedding space for sessions and items is created, and distance measures dissimilarity between the provided sequence of users' events and the next action. We discuss and compare metric learning approaches to commonly used learning-to-rank methods, where some synergies exist. We propose a simple architecture for problem analysis and demonstrate that neither extensively big nor deep architectures are necessary in order to outperform existing methods. The experimental results against strong baselines on four datasets are provided with an ablation study.