Session-based Sequential Skip Prediction via Recurrent Neural Networks

TL;DR

This paper presents a recurrent neural network approach for session-based sequential skip prediction, achieving top accuracy in WSDM cup 2019 by leveraging architecture choices and ensembling techniques.

Contribution

The paper introduces an effective RNN-based deep learning method with ensembling for skip prediction, winning the WSDM cup 2019 competition.

Findings

Achieved a Mean Average Accuracy of 0.648 on test data.

Ensembling multiple model variants improved accuracy.

Open-sourced implementation available on GitHub.

Abstract

The focus of WSDM cup 2019 is session-based sequential skip prediction, i.e. predicting whether users will skip tracks, given their immediately preceding interactions in their listening session. This paper provides the solution of our team \textbf{ekffar} to this challenge. We focus on recurrent-neural-network-based deep learning approaches which have previously been shown to perform well on session-based recommendation problems. We show that by choosing an appropriate recurrent architecture that properly accounts for the given information such as user interaction features and song metadata, a single neural network could achieve a Mean Average Accuracy (AA) score of 0.648 on the withheld test data. Meanwhile, by ensembling several variants of the core model, the overall recommendation accuracy can be improved even further. By using the proposed approach, our team was able to attain the 1st place in the competition. We have open-sourced our implementation at GitHub.