SAN FRANCISCO, June 17 (Xinhua) -- U.S. top financial service firm Visa Inc. said Monday its artificial intelligence (AI) tool has helped financial institutions prevent an estimated 25 billion U.S. dollars in fraud every year.
The AI-powered Visa Advanced Authorization (VAA) is a comprehensive risk management tool that monitors transaction authorizations on the Visa global payment network, or VisaNet, in real time to assist banking institutions in responding to emerging fraud patterns, Visa said.
The AI tool was employed to analyze all transactions, each in about one millisecond, by merchants so that banking institutions can approve legitimate purchases while blocking fraudulent deals.
Visa applied a neural network-based AI system in 1993 to assess the risks of transactions in real time.
"By striking the right balance between human expertise and technology innovation, we continue to evolve our capabilities as new AI breakthroughs expand the realm of what's possible," said Melissa McSherry, senior vice president and global head of Data, Risk and Identity Products and Solutions at Visa.
The San Francisco-based financial service provider said its VAA tool adopts machine learning models to detect each transaction for indicators of fraud and share information with card-issuing institutions to follow up transactions with account owners.
Visa processed more than 127 billion transactions between merchants and financial institutions on VisaNet in 2018.
More than 8,000 financial institutions in 129 countries and regions across the globe are using the VAA tool, Visa said.
