United StatesFinance and insurance2024 – ongoingMastercard
Generative AI detection of compromised cards and merchants
Mastercard reported a 2x detection rate for compromised cards with generative AI
Problem
Criminals advertised partial stolen card numbers online. Banks needed to identify the affected cards quickly enough to block further fraudulent transactions.
Approach
Mastercard built predictive technology using generative AI to infer compromised card details. It scanned transaction patterns across its network and alerted banks so they could block and reissue cards.
Results
Takeaway
The system connected partial evidence of stolen credentials with bank action. Mastercard did not disclose the evaluation sample or measurement period behind its reported improvements.
Categories
- Size
- Large enterprise
- Industry
- Finance and insurance
- Business function
- Finance, risk and legal
- Innovation type
- Process innovation
- AI technology
- Generative AIPredictive analytics and ML
- Adoption
- Built in-house
- Goal
- Quality and risk
- Evidence
- Company's own claim
Sources
Source summaries
Mastercard described operational use of its generative AI fraud detection technology. It claimed a doubled compromised-card detection rate and a 300% increase in merchant identification speed.
Full details are in the original sources.