Track Mix Generation on Music Streaming Services using Transformers

TL;DR

This paper presents Track Mix, a Transformer-based system for personalized playlist generation on Deezer, analyzing its advantages and challenges compared to traditional methods, and demonstrating its large-scale deployment for millions of users.

Contribution

It introduces a Transformer-based approach for music playlist generation and evaluates its effectiveness and challenges in a real-world streaming service context.

Findings

Track Mix generates personalized playlists for millions daily.

Transformers offer advantages over collaborative filtering in this setting.

The system faces specific technical challenges and limitations.

Abstract

This paper introduces Track Mix, a personalized playlist generation system released in 2022 on the music streaming service Deezer. Track Mix automatically generates "mix" playlists inspired by initial music tracks, allowing users to discover music similar to their favorite content. To generate these mixes, we consider a Transformer model trained on millions of track sequences from user playlists. In light of the growing popularity of Transformers in recent years, we analyze the advantages, drawbacks, and technical challenges of using such a model for mix generation on the service, compared to a more traditional collaborative filtering approach. Since its release, Track Mix has been generating playlists for millions of users daily, enhancing their music discovery experience on Deezer.