This paper describes an algorithm designed for Microsoft's Groove music service, which serves millions of users world wide. We consider the problem of automatically generating personalized music playlists based on queries containing a "seed" artist and the listener's user ID. Playlist generation may be informed by a number of information sources in- cluding: user specific listening patterns, domain knowledge encoded in a taxonomy, acoustic features of audio tracks, and overall popularity of tracks and artists. The importance assigned to each of these information sources may vary de- pending on the specific combination of user and seed artist. The paper presents a method based on a variational Bayes solution for learning the parameters of a model containing a four-level hierarchy of global preferences, genres, sub-genres and artists. The proposed model further incorporates a per- sonalization component for user-specific preferences. Em- pirical evaluations on both proprietary and public datasets demonstrate the effectiveness of the algorithm and showcase the contribution of each of its components.
|Title of host publication||WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining|
|Publisher||Association for Computing Machinery, Inc|
|Number of pages||9|
|State||Published - 2 Feb 2017|
|Event||10th ACM International Conference on Web Search and Data Mining, WSDM 2017 - Cambridge, United Kingdom|
Duration: 6 Feb 2017 → 10 Feb 2017
|Name||WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining|
|Conference||10th ACM International Conference on Web Search and Data Mining, WSDM 2017|
|Period||6/02/17 → 10/02/17|
Bibliographical notePublisher Copyright:
© 2017 ACM.