Anomaly Detection

Anomaly Detection

Application Description:

The Challenge

  • Paid $12.5 billion in Fines.
  • Detecting fraud proactively by monitoring emails, chats for AML, Insider Trading, Violation of Dodd-Frank
  • 600 million messages/month
  • Compliance team of < 30 people to review emails
  • Existing keyword-search systems generated too many false positives

Canopus Contributions

  • Delivered a semi-supervised NLP based learning solution
  • Coordinated multiple rounds of reviews to improve accuracy
  • Attained precision asked in SLA in less than 6 months
  • Responsible for end-to-end coordination

Benefits Realized

  • Defined, envisioned and developed a robust e-Communication surveillance program for the World’s largest financial institution
  • Enabled processing of large amounts of textual data to detect and score potentially fraudulent activities
  • Developed a prototype of the application that was subsequently enhanced to serve as the foundation of contract intelligence (COIN)

Related Projects