How to detect and classify credit card fraud? What is fraud for a person, say, buying expensive jewelry, spending on online casinos or simply spending a lot of money, is just the regular day-to-day for another. To make matters worse, the same people behave differently with different cards (personal card vs company card) and in different moments (“home mode” vs “vacation mode”), there are many different types of fraud and it changes very quickly. Finally, with millions of cards and billions of transactions and millisecond-level response times, the engineering scale of the problem is large. In this talk we will present the credit card fraud detection problem and an AI-driven solution based on FeedZai Pulse which has been deployed to a major payment processing company and that has significantly improved the previous solution.