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.

PDF, PS, HTML

In Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Istanbul, Turkey, May 2015.

@inproceedings{AAMAS2015-eladlieb, title={DJ-MC: A Reinforcement-Learning Agent for Music Playlist Recommendation}, author={Elad Liebman and Maytal Saar-Tsechansky and Peter Stone}, booktitle={Proceedings of the 14th International Conference on Autonomous Agents and Multiagent Systems (AAMAS)}, month={May}, address={Istanbul, Turkey}, url="http://www.cs.utexas.edu/users/ai-lab?liebman:aamas15", year={2015} }

Slides (PDF)