Mastercard Unveils Decision Intelligence Pro: A Game-Changer in Fraud Detection

In an exclusive announcement to CNBC, global payments giant Mastercard revealed the development of its proprietary generative artificial intelligence model, Decision Intelligence Pro.

This advanced AI solution is designed to assist thousands of banks within Mastercard's network in detecting and preventing fraudulent transactions.

Ajay Bhalla, the President of Mastercard's cyber and intelligence business unit, shared with CNBC that Decision Intelligence Pro enables banks to enhance their real-time assessment of suspicious transactions on the Mastercard network.

The AI model, a proprietary recurrent neural network at the core of generative AI, was crafted from scratch by Mastercard's cybersecurity and anti-fraud teams.

Bhalla explained, "We are using the transformer models, which basically help get the power of generative AI. 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."

While Mastercard occasionally leverages open-source technology, Bhalla emphasized that the majority of Decision Intelligence Pro's technology is developed in-house.

The proprietary algorithm has been trained using data from the staggering 125 billion transactions processed through Mastercard's card network annually.

Unlike large language models such as OpenAI's GPT-4 and Google's Gemini, Mastercard's AI focuses on understanding relationships between merchants rather than words.

This approach allows the AI to predict and identify fraudulent transactions by analyzing transaction data and patterns, providing an effective tool for combating financial fraud within the Mastercard network.

Source: Ryan Browne / CNBC