Mastercard has developed a proprietary generative AI model, named Decision Intelligence Pro, aimed at significantly enhancing fraud detection capabilities for thousands of banks on its network. This advanced AI solution is based on a recurrent neural network designed in-house, enabling real-time assessment of suspicious transactions to ascertain their legitimacy.
The technology leverages data from the approximately 125 billion transactions processed annually on Mastercard’s network, focusing on merchant relationships rather than textual analysis, to identify and predict fraudulent activities. Unlike traditional models, Mastercard’s AI analyzes cardholder merchant visit patterns to score transactions based on likelihood of legitimacy, all within a mere 50 milliseconds.
According to Ajay Bhalla, president of Mastercard’s cyber and intelligence business unit, this AI-driven approach has improved fraud detection rates by an average of 20%, with some instances seeing boosts up to 300%. Over the past five years, Mastercard has invested over $7 billion in cybersecurity and AI innovations, including acquisitions like the purchase of Swedish cybersecurity company Baffin Bay Networks in March 2023.
“We are using the transformer models which basically help get the power of generative AI,” Bhalla told CNBC in an exclusive interview earlier this week. “It’s all built in house we’ve got all kinds of data from the ecosystem. Because of the very nature of the business we are in, we see all the transaction data which comes to us from the ecosystem.”
Bhalla added that in some cases, Mastercard relies on open source “whenever needed,” but the “majority” of the technology is created in-house.
The deployment of this AI model not only positions Mastercard to reduce the financial burden of fraud on banks by potentially 20% but also underscores the company’s commitment to leading the charge in applying AI to enhance security and predict emerging fraud trends within the payment industry. This move comes amid broader industry shifts towards AI-enhanced financial services, evidenced by similar investments from competitors like Visa and new AI-based product launches from companies like PayPal.
“The beauty of Mastercard’s ecosystem is we see data from all our customers globally from these transactions,” said Bhalla. “What that does its it helps us actually see fraud and patterns across the ecosystem globally.”
Featured image: Credit: Ajay Bhalla
