On November 30, 2016, Mastercard announced Decision Intelligence, a fraud-detection and transaction-scoring service that uses artificial intelligence to evaluate card transactions in real time. The company described it as “the first use of AI being implemented on a global scale directly on the Mastercard network.”
The system’s stated goal was to reduce false declines - legitimate transactions wrongly rejected as fraud. Decision Intelligence builds a picture of how each account is normally used and scores incoming transactions against it, factoring in details such as customer value segmentation, risk profiling, location, merchant, device data, time of day, and type of purchase. It passes a predictive score to the card issuer, which can combine it with its own rules to approve or decline.
Ajay Bhalla, then Mastercard’s president of enterprise risk and security, framed the launch around the customer experience: “We are solving a major consumer pain point of being falsely declined when trying to make a purchase. By using AI technology on our global network, we’re helping financial institutions and merchants improve approval rates - and the consumer experience.”
The launch was an early example of machine learning being applied at the scale of a global payments network, where every transaction is scored in the moment. Mastercard continued to build on the brand, later layering generative AI onto the same Decision Intelligence line as fraud techniques evolved.