Mastercard’s real-time fraud detection technology will get a boost later this year when it rolls out the generative AI fraud detection tool it has developed.
The AI tool, called Decision Intelligence Pro (DI Pro) is powered by a recurrent neural network developed in-house by Mastercard’s cybersecurity and anti-fraud teams. The fraud detection algorithm is trained on billions of transactions that Mastercard processes each year.
The model learns from cardholders’ purchasing histories to understand the relationship between merchants and cardholders.
When a cardholder initiates a transaction, DI Pro scans a trillion data points to predict whether a transaction is likely to be fraudulent or not. It works out how likely the cardholder is to transact with the business based on a history of merchant visits.
In less than 50 milliseconds, DI Pro can predict whether the transaction is likely genuine or should be flagged as fraudulent.
DI Pro is expected to be implemented later this year but initial modeling shows it could 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, deflecting the efforts of criminals, and protecting banks and their customers. Supercharging our algorithm will improve our ability to anticipate the next potential fraudulent event, instilling trust into every interaction,” said Ajay Bhalla, president of Cyber and Intelligence at Mastercard.
Besides protecting cardholders from fraud, Bhalla said DI Pro would also “reduce the number of false positives by more than 85%.”
Banks spend a significant portion of their operational costs on fraud detection. A 20% reduction in fraudulent transactions translates into reduced human and financial resources needed to assess illegitimate transactions.
