Mastercard is adopting generative AI techniques to enhance the protections that keep consumers and the entire payments network, safe. Specifically, Mastercard is deploying gen-AI to enhance its Decision Intelligence (DI) offering.
The real-time decisioning solution already helps banks score and safely approve 125 billion transactions a year. Mastercard says that new generative AI technology will scan an unprecedented one trillion data points. The tool will predict whether a transaction is likely to be genuine or not. This builds on Mastercard’s existing ability to analyse account, purchase, merchant and device information in real time.
Boosting fraud detection rates by an average of 20%
The next-gen technology, DI Pro, works by assessing the relationships between multiple entities surrounding a transaction to determine its risk. In less than 50 milliseconds, this technology improves the overall DI score, sharpening the data provided to banks.
Initial modelling shows AI enhancements boost fraud detection rates on average by 20% and as high as 300% in some instances.
“With generative AI we are transforming the speed and accuracy of our anti-fraud solutions. This deflects the efforts of criminals, and protects banks and their customers. Supercharging our algorithm will improve our ability to anticipate the next potential fraudulent event. It instils trust into every interaction,” said Ajay Bhalla, President of Cyber and Intelligence at Mastercard.
The enhancement of DI will further improve banks’ abilities to protect cardholders from fraudulent transactions and mitigate what are known as known as false positives. That is, legitimate transactions which are incorrectly flagged as fraudulent ones.
“The precision of the solution is achieved by scanning potential points of sale in real time. It been shown in our own analysis to not only increase accuracy. But it also reduces the number of false positives by more than 85%,” said Bhalla.