compliance_monitoring · workflow
Instacart builds real-time fraud detection with Yoda decision platform and ClickHouse
Instacart needed to detect a wide variety of fraudulent patterns — including fake accounts, payment fraud, and customer-shopper collusion — in real time to protect its financial health and platform trust, while keeping latency low enough for in-transaction decisioning.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Analyst manages fraud rules
Analysts create, read, update, and delete fraud detection rules through a UI.
Tools used
YodaClickHouseDebezium's Postgres connectorKafkaKafka ConnectFlinkmachine learning inference servicesFeature Store
Outcome
Real-time fraud detection with Yoda resulted in millions of dollars a year in savings, and the shift to self-serve analyst-led rule creation reduced engineer time spent on heuristic development from 80% to 20%.
Results
Time saveddecreased from 80% to 20%
Cost replacedmillions of dollars a year
Grounding & classification
Source type: technical build writeup
26 fields verified against source quotes, 1 dropped as unverifiable.
anomaly detectionpredictive analyticspurchase orderhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedecommercecost reductionemployee productivitytechnical build writeupback office opscompliance monitoringextract classify routemonitor detect alert