Visa unveils AI fraud shield to cut A2A fraud by 50%

Visa has unveiled an enhanced account-to-account (A2A) fraud prevention solution designed to help financial institutions detect and stop fraudulent transactions in real time before money leaves customers’ accounts. The payments giant said its upgraded A2A Protect has demonstrated the ability to reduce more than 50 percent of fraud while cutting unnecessary fraud alerts by over 40 percent, as banks face growing pressure to protect rapidly expanding instant payment channels without disrupting legitimate transactions. The enhanced solution introduces a new unified fraud score, marking Visa’s first combined in-market offering incorporating technology from Featurespace, the fraud and financial crime prevention company acquired by Visa. Visa said the new score gives financial institutions faster and clearer risk signals by combining its payment network intelligence with Featurespace’s technology, enabling banks to identify suspicious A2A transactions earlier. The move comes as A2A payments continue to expand globally, with A2A transactions projected to exceed 5.8 trillion by 2028, representing a 160 percent increase from 2024. Unlike conventional fraud models that require months of transaction data to develop intelligence, A2A Protect uses artificial intelligence and transfer learning to provide banks with immediate access to global risk insights. Financial institutions that opt into Visa’s network-level intelligence sharing can also receive additional signals showing emerging scam hotspots and coordinated fraudulent activity across the payments ecosystem. According to Visa, such intelligence can provide banks with an earlier and broader view of threats that may be difficult for individual institutions to identify from their own transaction data, helping them detect potential scams before transactions are authorised. “Fraudsters move fast across payment types, and financial institutions need risk insights just as quickly, without slowing down legitimate payments,” said Walter Lironi, senior vice president and head of value-added services, Central and Eastern Europe, Middle East and Africa (CEMEA), Visa. “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,” he said. Visa said A2A Protect can be integrated into existing financial institution systems through a single API, potentially reducing implementation time and technical complexity. The solution also provides plain-language explanations with each fraud alert, allowing fraud teams to understand why a transaction was flagged and respond without unnecessarily blocking genuine customers. The development highlights the growing importance of network-level intelligence as real-time payments become more widespread and fraudsters increasingly move between payment channels. By combining transaction-level risk assessment with broader ecosystem signals, Visa is positioning A2A Protect as a preventive layer aimed at identifying fraudulent activity before funds are transferred rather than relying solely on investigations after money has left an account. Join BusinessDay whatsapp Channel, to stay up to date Open In Whatsapp