Detecting and Mitigating Fraud at Scale

Print Friendly, PDF & Email

The presentation below by Eric Levine, Engineering Manager at Airbnb shows how Airbnb’s Trust and Safety team has built machine learning infrastructure from the ground up to catch and defuse fraudsters on the platform. This talk briefly goes through the history of the machine learning platform from its very basic roots to the advanced system that is in place today. The team found that by taking a tightly coupled, naïve implementation to a well-factored, cleanly separated systems, it could individually tune each component to decrease the cycle between bad behavior to well-performing model to catch said behavior, and how it could leverage that introspection to enable real-time detection of issues at scale. Further, by empowering data science to explore new features independently from engineering efforts, the team was able to reduce the time from feature conception to production implementation.



Sign up for the free insideBIGDATA newsletter.

Speak Your Mind