Mastercard launches GenAI fraud detection

Mastercard has introduced a new AI tool to combat fraud. Decision Intelligence Pro is “an advanced iteration of its renowned Decision Intelligence (DI) real-time decisioning solution” a Gen AI consumer protection tool that determines transaction risk by assessing entity relationships.

Mastercard launches GenAI fraud detection tool

In response to the escalating challenges in the cybersecurity landscape, Mastercard is adopting generative AI techniques to elevate the protective measures that safeguard consumers and the payments ecosystem.

The solution, which is slated to become available later this year, leverages generative AI to scrutinise an unprecedented 1 trillion data points, predicting the authenticity of transactions.

The technology swiftly assesses relationships between multiple entities involved in a transaction, significantly improving the overall DI score in less than 50 milliseconds.

This iteration enhances Mastercard’s existing capability to analyse account, purchase, merchant, and device information in real-time.

Initial modelling of Decision Intelligence Pro reveals remarkable results, showcasing an average 20% increase in fraud detection rates and spikes as high as 300% in certain instances.

The offering not only elevates accuracy but also tackles the issue of false positives.

By scanning potential points of sale in real-time, Decision Intelligence Pro demonstrates a reduction of more than 85% in false positives, ensuring that legitimate transactions are not incorrectly flagged as fraudulent.

“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,” says Ajay Bhalla, president of Cyber and Intelligence at Mastercard.

“Supercharging our algorithm will improve our ability to anticipate the next potential fraudulent event, instilling trust into every interaction.

The precision of the solution – achieved by scanning potential points of sale in real time – has been shown in our own analysis to not only increase accuracy, but also reduce the number of false positives by more than 85%.”