BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Groove Radio: A Bayesian Hierarchical Model for Personalized Playl
 ist Generation - Noam Koenigstein (Microsoft Research)
DTSTART:20170209T150000Z
DTEND:20170209T160000Z
UID:TALK69724@talks.cam.ac.uk
CONTACT:Liang Wang
DESCRIPTION:This talk describes an algorithm designed for Microsoft's Groo
 ve music service\, which serves millions of users world wide.  We consider
  the problem of automatically generating personalized music playlists base
 d on queries containing a ``seed'' artist and the listener's user ID.\n\nP
 laylist generation may be informed by a number of information sources incl
 uding: user specific listening patterns\, domain knowledge encoded in a ta
 xonomy\, acoustic features of audio tracks\, and overall popularity of tra
 cks and artists. The importance assigned to each of these information sour
 ces may vary depending on the specific combination of user and seed artist
 .\n\nThe work presents a method based on a variational Bayes solution for 
 learning the parameters of a model containing a four-level hierarchy of gl
 obal preferences\, genres\, sub-genres and artists. The proposed model fur
 ther incorporates a personalization component for user-specific preference
 s. Empirical evaluations on both proprietary and public datasets demonstra
 te the effectiveness of the algorithm and showcase the contribution of eac
 h of its components.\n\nBio: Noam Koenigstein received his Ph.D. degree in
  Electrical Engineering from Tel-Aviv University\, Tel-Aviv\, Israel in 20
 14. From 2012 he holds a researcher position in Microsoft R&D Center in He
 rzeliya\, Israel. Since 2014 he manages the machine learning and recommend
 ations research team responsible for designing and building recommendation
  algorithms for a wide array of Microsoft products such as Windows store\,
  Xbox\, Groove music\, and Windows phone serving millions around the globe
 . The team balances applied work with academic impact by publishing and pa
 rticipating in relevant conferences (e.g.\, KDD\, ICML\, NIPS\, RecSys\, W
 WW\, etc).
LOCATION:FW26\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR