DJ-MC: A Reinforcement-Learning Agent for Music Playlist Recommendation
This addresses music recommendation for listeners by modeling temporal context, but it is incremental as it builds on existing reinforcement-learning approaches for sequences.
The paper tackled the problem of music playlist recommendation by developing DJ-MC, a reinforcement-learning framework that models preferences for songs and transitions to recommend sequences, and results showed it significantly improved over methods ignoring transitions in human evaluations.
In recent years, there has been growing focus on the study of automated recommender systems. Music recommendation systems serve as a prominent domain for such works, both from an academic and a commercial perspective. A fundamental aspect of music perception is that music is experienced in temporal context and in sequence. In this work we present DJ-MC, a novel reinforcement-learning framework for music recommendation that does not recommend songs individually but rather song sequences, or playlists, based on a model of preferences for both songs and song transitions. The model is learned online and is uniquely adapted for each listener. To reduce exploration time, DJ-MC exploits user feedback to initialize a model, which it subsequently updates by reinforcement. We evaluate our framework with human participants using both real song and playlist data. Our results indicate that DJ-MC's ability to recommend sequences of songs provides a significant improvement over more straightforward approaches, which do not take transitions into account.