Fraud does not wait for batch. To block funds from moving, Coinbase models need the right features at the right time—fresh, consistent, and served with predictable low latency.This session explains Coinbase’s Databricks-based feature platform for real-time fraud ML: Real-Time Mode on Structured Streaming; declarative Feature APIs + CI/CD (features as code); AI/agent-assisted migration and feature creation; and Lakebase feature serving targeting p99 90% streaming infra cost reduction and up to >95% p99 freshness improvement. Moving self-built batch feature sets to a managed feature store is also driving an estimated ~25–35% productivity gain by retiring bespoke pipelines and shrinking the on-call surface. Attendees leave with a reference architecture + migration playbook across latency, reliability, and TCO.
These frauds exploit emotional vulnerability and trust rather than technical weaknesses.
- Romance Scams: Scammers build long-term online relationships with victims, eventually fabricating a “crisis” (medical emergency, legal trouble, or travel costs) that requires the victim to send money.
- Pig Butchering: A hybrid scam where the criminal builds a romantic or platonic relationship to eventually “tutor” the victim in a fraudulent cryptocurrency investment.