Mastercard has announced the launch of a new artificial intelligence (AI) model that can help banks detect and prevent fraud and other financial crimes in real time.

The model, called Brighterion, uses a natural language generation (NLG) technique similar to the popular GPT-3 model, which can produce coherent and fluent texts on various topics. Brighterion can explain its reasoning and actions to human analysts, making it more transparent and trustworthy than traditional rule-based systems.

Brighterion can also learn from new data and adapt to changing patterns of fraud, without requiring manual retraining or supervision. This makes it more agile and responsive to emerging threats and challenges in the financial sector.

According to Mastercard, Brighterion can reduce false positives by up to 50% and increase fraud detection by up to 30% compared to traditional rule-based systems. This can save banks time and money, as well as improve customer satisfaction and loyalty.

Brighterion is part of Mastercard’s broader strategy to leverage AI and data analytics to provide value-added services to its customers and partners. Mastercard has been investing in AI and data capabilities for over 20 years, and has acquired several companies in this field, such as NuData Security, RiskRecon, and Ekata.

Mastercard’s president of cyber and intelligence solutions, Ajay Bhalla, said: “We are proud to introduce Brighterion, a cutting-edge AI model that can help banks combat fraud and financial crimes in real time. Brighterion is not only fast and accurate, but also transparent and explainable, which is crucial for building trust and confidence in AI. Brighterion is another example of how Mastercard is using AI and data to create a safer and more inclusive digital economy.”