United KingdomFinance and insurance2024 – ongoingRevolut
AI card-scam detection and payment blocking
Revolut reported 30% lower investment card-scam losses after introducing AI payment checks
Problem
Scammers persuaded customers to authorize card payments for supposed investments. Ordinary payment authorization could therefore approve a transaction that harmed the customer.
Approach
Revolut's financial crime team built a machine-learning system to identify likely scam payments and decline them. Customers then entered an intervention flow with additional questions and scam warnings. Suspected victims could also speak with a fraud specialist.
Results
Takeaway
The payment block was linked to a customer intervention process. The reported loss reduction concerned investment-related card scams, rather than fraud across the bank.
Categories
- Size
- Large enterprise
- Industry
- Finance and insurance
- Business function
- Finance, risk and legal
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Goal
- Quality and risk
- Evidence
- Company's own claim
Sources
Source summaries
Revolut described an internally built payment detector available worldwide. It reported a 30% reduction in investment-related card-scam losses and explained how declined payments led to further customer checks.
Full details are in the original sources.