Sequential Skip Prediction with Few-shot in Streamed Music Contents

TL;DR

This paper describes algorithms for predicting track skips in streamed music sessions using limited acoustic data, demonstrating that sequence learning outperforms metric learning and that user logs significantly enhance prediction accuracy.

Contribution

Introduces sequence learning algorithms for skip prediction in streamed music, highlighting the effectiveness of user logs and advancing methods for limited data scenarios.

Findings

Sequence learning outperforms metric learning in skip prediction.

Using complete user logs significantly improves prediction accuracy.

Algorithms achieve competitive performance in the WSDM Cup 2019 challenge.

Abstract

This paper provides an outline of the algorithms submitted for the WSDM Cup 2019 Spotify Sequential Skip Prediction Challenge (team name: mimbres). In the challenge, complete information including acoustic features and user interaction logs for the first half of a listening session is provided. Our goal is to predict whether the individual tracks in the second half of the session will be skipped or not, only given acoustic features. We proposed two different kinds of algorithms that were based on metric learning and sequence learning. The experimental results showed that the sequence learning approach performed significantly better than the metric learning approach. Moreover, we conducted additional experiments to find that significant performance gain can be achieved using complete user log information.