BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Music Recommender Systems - Smriti Pramanick\, Sidney Sussex Colle
 ge
DTSTART:20161123T190000Z
DTEND:20161123T193000Z
UID:TALK69168@talks.cam.ac.uk
CONTACT:Matthew Ireland
DESCRIPTION:Music recommender systems have become a crucial part of severa
 l music players\, like Spotify\, Pandora\, Apple Music\, and Google Play M
 usic. Music recommender systems are inherently more complex than other rec
 ommender systems (like recommender systems for shopping) because of the su
 bjective nature of music and the ability for users’ preferences to modul
 ate with mood. In this talk\, we will define the components of a music rec
 ommender system and discuss several approaches to music recommending. We w
 ill also explore one of the more popular approaches\, a content-based algo
 rithm\, in more depth. Finally\, we will dive into a case study of Spotify
 ’s recommender system\, by taking a look at its automatically curated Di
 scover Weekly playlists that are personalized for each user.
LOCATION:Wolfson Hall\, Churchill College
END:VEVENT
END:VCALENDAR