BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Recommender systems - Aidan Brocklebank\, Churchill College
DTSTART:20210303T200000Z
DTEND:20210303T203000Z
UID:TALK157960@talks.cam.ac.uk
CONTACT:Matthew Ireland
DESCRIPTION:It is increasingly the case that every website or platform use
 rs visit wants to give them recommendations\, for videos\, songs\, product
 s\, articles\, movies and more. Over the last few decades\, the commercial
  world has realised how effective the data derived from user behaviours ca
 n be in determining what you want before you even want it\, and recommende
 r systems are what make this possible.\n\nIn this talk I will showcase fou
 r major approaches to making recommendations\, from simple early systems t
 o more modern machine learning models\, discussing the data needed to make
  them work\, the process\, and their pros and cons.\n
LOCATION:Online\, via MS Teams
END:VEVENT
END:VCALENDAR