Visa has upgraded its A2A Protect product with a unified fraud score designed to give banks real-time risk signals on account-to-account transfers, with the aim of stopping fraud before a transaction completes.
The update marks Visa’s first in-market integration of Featurespace technology, an AI-based fraud detection system the payments company acquired.
The combined tool assigns a single score to each transaction and delivers a plain-language explanation of why it was flagged, so fraud teams can act without reviewing complex model outputs or disrupting genuine customers.
The timing reflects the scale of what is at stake. Account-to-account payment volumes are projected to surpass 5.8 trillion transactions by 2028, a 160 per cent increase from 2024 levels, according to Visa. As volumes climb, so does the surface area for fraud.
“Fraudsters move fast across payment types, and financial institutions need risk insights just as quickly, without slowing down legitimate payments. A2A Protect combines Visa’s network expertise with Featurespace’s technology to deliver a powerful new layer of protection that helps financial institutions detect more fraud, earlier,” Walter Lironi, Senior Vice President, Head of Head of Value-Added Services, Central and Eastern Europe, Middle East, and Africa (CEMEA), Visa said in a statement.
One feature of the updated product is the option for banks to share network-level signals. Institutions that opt in gain visibility into emerging scam hotspots and coordinated fraud patterns that would be difficult to detect from their own transaction data alone.
Banks that do not opt in can still access Visa’s global risk intelligence from day one, without waiting to accumulate their own historical data or for other banks to join a shared consortium.
A2A Protect connects to existing bank systems through a single API, which Visa says reduces implementation time and complexity.
