BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Online Machine Learning Methods - Streams of Financially Important
  News. - Miles Osbourne\, Bloomberg
DTSTART:20160422T120000Z
DTEND:20160422T131500Z
UID:TALK65522@talks.cam.ac.uk
CONTACT:Jan Samols
DESCRIPTION:Twitter nowadays is more than just stories about cats in trees
  and what I had for dinner. It is now a serious source of market moving ne
 ws - stories on Twitter that can cause real changes in stock markets.  \n\
 nBut with hundreds of millions of posts per day\, how can we quickly ident
 ify stories that matter to our clients?  \n\nI will sketch how we used onl
 ine machine learning methods to find and organise incoming stories into re
 al time streams of related content\, processing more than 8k tweets per se
 cond on a single core. Along the way I will talk about open problems such 
 as trust\, multilinguality and market manipulation.\n\n\n
LOCATION:FW11\, Computer Laboratory
END:VEVENT
END:VCALENDAR