Recurrent Neural Networks with Top-k Gains for Session-based Recommendations
This work addresses session-based recommendation systems for users, offering incremental improvements through tailored loss functions and optimizations.
The authors tackled the problem of session-based recommendations by introducing novel ranking loss functions for RNNs, resulting in improvements of up to 35% in MRR and Recall@20 over previous RNN solutions and up to 53% over classical collaborative filtering approaches.
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.