Italy’s Banks Get Boost in Fight Against Fraud with AI-Powered Detection System

In a major breakthrough in the fight against online fraud, Mastercard has unveiled an innovative algorithm that uses generative AI and graph technology to detect compromised credit cards at double the previous rate. This new system is expected to revolutionize the way banks identify and prevent fraudulent transactions.

The Challenge of Identifying Compromised Cards

According to Yatin Katyal, part of the team that developed the algorithm at Mastercard’s AI Garage in Gurgaon, India, the biggest challenge was identifying compromised cards on illegal websites where only a portion of the 16-digit card number was available.

Overcoming the Hurdle

To overcome this hurdle, Mastercard’s data scientists used graph technology to track relationships between data points and identify patterns in fraudulent activity. The algorithm also relies on generative AI, which trains itself to create new content based on large datasets.

How the System Works

The system works by analyzing recent fraud transactions, known or suspected compromised merchants, and other signals such as testing pre-authorized transactions to scan for recent activity that could be fraudulent. It then uses advanced algorithms to predict the full 16-digit card number of compromised cards and the likelihood of them being used by criminals.

Benefits of the Algorithm

This information will enable banks to block suspect cards much faster than previously possible, significantly reducing the risk of fraud. The algorithm can also track activity across the Mastercard network, making it more efficient in detecting and preventing fraudulent transactions.

Real-World Impact

The technology has already been incorporated into Cyber Secure, enabling issuers and merchants to better understand and assess cyber risk across their systems, preventing potential breaches.

Quote from Yatin Katyal

“Using graph database technology, we are able to predict the full 16-digit card numbers of these compromised cards and the likelihood of such cards being used by criminals,” said Katyal. “This information will enable banks to block suspect cards much faster than previously possible.”

Impact on Italy’s Banking Sector

The impact of this technology is expected to be significant in reducing online fraud in Italy’s banking sector, where millions of euros are lost every year due to fraudulent transactions.