# Recurrent Neural Networks with Top-k Gains for Session-based Recommendations

## TL;DR

This paper introduces novel ranking loss functions for RNNs in session-based recommendations, significantly improving performance without increasing training time and validated through online A/B testing.

## Contribution

The paper proposes new ranking loss functions tailored for RNNs in session-based recommendation systems, achieving substantial performance gains.

## Key findings

- Up to 35% improvement in MRR and Recall@20 over previous RNN methods.
- Up to 53% improvement over classical collaborative filtering.
- Performance gains confirmed in online A/B testing.

## Abstract

RNNs have been shown to be excellent models for sequential data and in particular for data that is generated by users in an session-based manner. The use of RNNs provides impressive performance benefits over classical methods in session-based recommendations. In this work we introduce novel ranking loss functions tailored to RNNs in the recommendation setting. The improved performance of these losses over alternatives, along with further tricks and refinements described in this work, allow for an overall improvement of up to 35% in terms of MRR and Recall@20 over previous session-based RNN solutions and up to 53% over classical collaborative filtering approaches. Unlike data augmentation-based improvements, our method does not increase training times significantly. We further demonstrate the performance gain of the RNN over baselines in an online A/B test.