BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning item trees for collaborative filtering with implicit feed
 back - Dr Andriy Mnih (Gatsby Unit\, UCL)
DTSTART:20101130T110000Z
DTEND:20101130T120000Z
UID:TALK27917@talks.cam.ac.uk
CONTACT:Peter Orbanz
DESCRIPTION:User preferences can be inferred from either explicit feedback
 \, such as item ratings\, or implicit feedback\, such as rental histories.
  Research in\ncollaborative filtering concentrated on explicit feedback du
 e to the ease of formalization\, resulting in the development of accurate 
 and scalable\nmodels. However\, since explicit feedback is often difficult
  to collect\, it is essential to develop effective models that take advant
 age of the\nmore abundant  implicit feedback.\n\nWe introduce a new approa
 ch to implicit feedback collaborative filtering based on modelling the ite
 m selection process performed by each user. In\norder to make it feasible 
 to learn a different distribution over items for each user\, we restrict o
 ur attention to tree-structured distributions.\nSince the accuracy of the 
 resulting model is heavily dependent on the choice of the tree structure\,
  we develop an algorithm for learning trees\nfrom data. Our algorithm is b
 ased on the online EM formalism and takes into account the probabilistic m
 odel the trees will be used with.\n\nJoint work with Yee Whye Teh\n
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR