On Wednesday, Visa announced the launch of an AI-based product to combat token fraud, Visa Provisioning Intelligence (VPI).
The new service will utilize machine learning models to predict the probability of token fraud before it happens, officials said. Available as a value-added service, VPI rates the likelihood of fraud for token provisioning requests, which will help financial institutions prevent fraud in a targeted way and enable more seamless and secure transactions for cardholders.
“While tokenization is one of the most secure ways to transact, we’re seeing fraudsters use social engineering and other scams to illegitimately provision tokens,” James Mirfin, SVP and global head of risk and identity solutions at Visa, said. “With VPI, we’re leveraging Visa’s vast network and data insights to help clients detect and prevent provisioning fraud before it happens.”
Tokenization is technology that protects consumers’ account information by replacing account numbers with a unique code. Visa said, however, token provisioning fraud losses by bad actors reached an estimated $450 million globally in 2022.
The VPI technology rates each token provision request for its probability of being fraudulent in real-time between 1 and 99, with 99 being the highest probability of fraud. Using a segment-level supervised machine learning model, the service can identify patters in past token requests across devices, e-commerce and card-on-file tokens to predict the probability of fraud.
The technology allows users to detect provisioning fraud and decline a token provisioning request before the fraud occurs, and accurately separates fraudulent activity from non-fraudulent activity, officials said.