Generating Music Playlists with Hierarchical Clustering and Q-Learning

Automatically generating playlists of music is an interesting area of research at present, with many online services now offering “radio channels” which attempt to play through sets of tracks a user is likely to enjoy. However, these tend to act as recommendation services, introducing a user to new music they might wish to listen to. Far less effort has gone into researching tools which learn an individual user’s tastes across their existing library of music and attempt to produce playlists fitting to their current mood. This paper describes a system that uses reinforcement learning over hierarchically-clustered sets of songs to learn a user’s listening preferences. Features extracted from the audio are also used as part of this process, allowing the software to create cohesive lists of tracks on demand or to simply play continuously from a given starting track. This new system is shown to perform well in a small user study, greatly reducing the relative number of songs that a user skips.

[1]  Masataka Goto,et al.  An Efficient Hybrid Music Recommender System Using an Incrementally Trainable Probabilistic Generative Model , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[2]  Michael J. Pazzani,et al.  Content-Based Recommendation Systems , 2007, The Adaptive Web.

[3]  John C. Platt,et al.  Learning a Gaussian Process Prior for Automatically Generating Music Playlists , 2001, NIPS.

[4]  Thorsten Joachims,et al.  Playlist prediction via metric embedding , 2012, KDD.

[5]  Gert R. G. Lanckriet,et al.  Hypergraph Models of Playlist Dialects , 2012, ISMIR.

[6]  Chris Watkins,et al.  Learning from delayed rewards , 1989 .

[7]  Ichiro Fujinaga,et al.  jAudio: An Feature Extraction Library , 2005, ISMIR.

[8]  Thierry Bertin-Mahieux,et al.  The Million Song Dataset , 2011, ISMIR.

[9]  R. Bellman.  A Markovian Decision Process , 1957 .

[10]  Jane Yung-jen Hsu,et al.  A Reinforcement Learning Approach to Emotion-based Automatic Playlist Generation , 2010, 2010 International Conference on Technologies and Applications of Artificial Intelligence.

[11]  Chun Chen,et al.  Music recommendation by unified hypergraph: combining social media information and music content , 2010, ACM Multimedia.

[12]  Dan Frankowski,et al.  Collaborative Filtering Recommender Systems , 2007, The Adaptive Web.

[13]  Yehuda Koren,et al.  Factorization meets the neighborhood: a multifaceted collaborative filtering model , 2008, KDD.

[14]  Jialie Shen,et al.  Just-for-Me: An Adaptive Personalization System for Location-Aware Social Music Recommendation , 2014, ICMR.

[15]  Gert R. G. Lanckriet,et al.  The Natural Language of Playlists , 2011, ISMIR.

[16]  Tim Pohle,et al.  Dynamic Playlist Generation Based on Skipping Behavior , 2005, ISMIR.

[17]  J. Platt.  Fast embedding of sparse music similarity graphs , 2003, NIPS 2003.

[18]  Markus Schedl,et al.  Mobile Music Genius: Reggae at the Beach, Metal on a Friday Night? , 2014, ICMR.

[19]  Dietmar Jannach,et al.  Analyzing the Characteristics of Shared Playlists for Music Recommendation , 2014, RSWeb@RecSys.

[20]  Yifan Hu,et al.  Collaborative Filtering for Implicit Feedback Datasets , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[21]  Peter Stone,et al.  DJ-MC: A Reinforcement-Learning Agent for Music Playlist Recommendation , 2014, AAMAS.