/security

News and resources on cyber and physical threats to banks and fintechs worldwide.

Mastercard supercharges fraud detection with GenAI

Mastercard is turbocharging its fraud detection technology with generative AI that can scan a trillion data points to predict whether a transaction is likely to be genuine or not.

  9 1 comment

Mastercard supercharges fraud detection with GenAI

Editorial

This content has been selected, created and edited by the Finextra editorial team based upon its relevance and interest to our community.

The payments giant's Decision Intelligence tool already helps banks score and safely approve 143 billion transactions a year.

The new Decision Intelligence Pro works by assessing the relationships between multiple entities surrounding a transaction to determine its risk. In less than 50 milliseconds, the 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, claims Mastercard.

This should help banks protect cardholders from fraudulent transactions and mitigate false positives, where legitimate payments are incorrectly flagged.

Ajay Bhalla, president, cyber and intelligence, Mastercard, says: “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 is tapping into GenAI in a host of ways, including for a recently unveiled retail assistant tool that offers shoppers tailored product recommendations.

Learn more about payments at NextGen Nordics on the 23 April 2024.

Sponsored [Webinar] Operational Resilience in the age of DORA

Related Company

Keywords

Comments: (1)

Ketharaman Swaminathan

Ketharaman Swaminathan Founder and CEO at GTM360 Marketing Solutions

Trillion data points? Can we get a sample of just one billion of them??

[On-Demand Webinar] PREDICT 2025: The Future of AI in the USFinextra Promoted[On-Demand Webinar] PREDICT 2025: The Future of AI in the US