Mastercard Applies Generative AI Model for Bank Fraud Detection
Mastercard is rolling out a new generative AI-powered tool to bolster protections against fraud for banks and consumers. The Decision Intelligence Pro enhances the existing system for real-time transaction analysis to scan a trillion data points and boost fraud detection rates by an average of 20% and reaching 300% improvements with some transactions.
Generative AI Financial ID
Decision Intelligence Pro works by rapidly assessing relationships between various entities like the account, purchase details, merchant, and device. The upgraded precision also reduces false positives, where legitimate transactions are incorrectly flagged as fraudulent, by over 85% in tests. Mastercard described the new setup as a way to strengthen cybersecurity at a time when fraudsters are increasingly exploiting generative AI techniques and told. The upgraded Decision Intelligence is necessary to stay ahead of new threats and vulnerabilities, and Mastercard hopes it will make people feel better about relying on digital transactions. Decision Intelligence Pro will start rolling out later this year.
“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,” Mastercard president of cyber and intelligence Ajay Bhalla explained. “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%.”
This isn’t the first foray into generative AI for Mastercard in recent months. The company debuted Shopping Muse in December under its Dynamic Yield subsidiary. Shopping Muse is designed to mimic the human experience in retail by understanding and responding to consumers’ colloquial language, thus offering tailored product recommendations and suggestions for coordinating items.
Follow @voicebotaiFollow @erichschwartz
