kyc_aml · finance · workflow
CBA cuts scam losses by 70% using real-time GenAI from H2O.ai
CBA faced mounting fraud and scam losses that required AI-driven intervention to protect its large customer base at scale.
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 · Real-time multi-model processing
Thousands of models run over billions of data points in real time to power the customer engagement engine.
Tools used
H2O.ai
Outcome
CBA achieved a 30% fraud reduction and 70% scam reduction overall, with customer scam losses down 76% from their 2022 peak.
Results
Volume16M+
Cost replaced30%
Grounding & classification
Source type: vendor customer story
21 fields verified against source quotes, 1 dropped as unverifiable.
anomaly detectionfraud detectionpredictive analyticsmetric backedproduction runtime claimedsource backedtools describedworkflow describedbankingcost reductioncustomer satisfactionerror reductionvendor customer storycustomer supportkyc amlmonitor detect alert