Recent AI upgrades to Adaptive Acceptance led to a record $6 billion in false declines recovered in 2024—a 60% year-over-year increase.

With the rise of usage-based billing for AI services, the strategic importance of credits is growing. That’s why we’ve recently added a new credits feature to Stripe Billing.

We created a usage-based billing system with an accurate and highly available revenue ledger; real-time events processing with ultrahigh throughput billing; and the ability to support complex pricing models and accurate billing, even in the face of delayed events. Doing so required reimagining how to build a highly scaled, highly reliable event streaming platform.

With our slice monitoring program, we use machine learning to spot small pockets of performance declines amid the sea of global payments.

While Radar’s models predict the likelihood of fraud or card testing, we needed a new way to recognize verification attacks that were causing higher-than-average authorization rates. Learn about our three-layered approach to combating this new fraud trend.

In the third and final installment in our three-part series, we examine the most important questions for the future of real-time payments: will they ever take off in the US and the UK, and will they emerge as a truly global payment method?

Card testing is one of the most significant fraud threats to Stripe, its users, and the broader financial ecosystem. Stripe’s machine learning–based approach—based on rapid detection and retraining—has led to successful card testing attacks on Stripe decreasing by 80% over the last two years.

To compete with other payment methods for consumer preference, real-time payments are expanding their “bundle” of services to include subscriptions, credit, and in-person transactions.

Payment methods are tightly woven into the economic and social fabric of a country. In most countries, the dominant means of exchange has rarely pivoted—and yet in many places around the world, it’s changing right now with real-time payments. Here’s why.

By applying ML to the process of navigating Strong Customer Authentication requirements, we’re helping users reduce checkout friction while lowering fraud and increasing authorization rates.