BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:How to Fight Financial Crime with AI - David Sutton - Featurespace
DTSTART:20231122T140000Z
DTEND:20231122T150000Z
UID:TALK207220@talks.cam.ac.uk
CONTACT:James Fergusson
DESCRIPTION:Fraud and scams are now the most common crimes in the UK\, wit
 h hundreds of thousands of victims each year. As criminals move to adopt A
 I to attack consumers\, banks and financial institutions are in an AI arms
  race to improve detection and prevention. In this seminar\, researchers f
 rom the Innovation Lab at Featurespace will discuss open frontiers in AI r
 esearch that enable new sources of leverage on the problem. Generative AI 
 methods have revealed their potential as a tool to improve consumer protec
 tion\, however adapting them for use with structured\, entity-oriented tim
 e series data is not straightforward. Collaborative AI systems\, which ope
 rate in a federated manner across banks\, have also shown a lot of promise
  for fraud prevention\, but open up new challenges of their own for consum
 er privacy and data protection\, which need to be overcome.\n\nFeaturespac
 e is a Cambridge-based AI company that specializes in fighting financial c
 rime. After being spun out of the Engineering Department in 2008\, it has 
 grown to employ more than 400 people\, and has deployed systems to around 
 100 banks worldwide. The company recently launched TallierLTM\, the first 
 pre-trained Large Transaction Model trained across hundreds of millions of
  consumer accounts.\n
LOCATION:Maxwell Centre
END:VEVENT
END:VCALENDAR