Stripe Radar
Learn about our integrated solution for fraud protection.
Stripe Radar is a suite of modern tools to help you fight fraud. It’s fully integrated into your payments flow and you can start using it without any additional development time.
At the center of Stripe Radar is a machine learning system that provides real-time transaction scoring based upon thousands of signals about each incoming card payment. Our system also uses data across Stripe’s network of millions businesses to evaluate the level of risk for each payment you process, and has shielded businesses on Stripe from millions of attempted fraudulent payments.
Features
Stripe Radar, our core machine learning engine, and Radar for Fraud Teams, an add-on suite of tools for fraud professionals, offer the following key features.
| Stripe Radar | Stripe Radar For Fraud Teams |
|
|---|---|---|
| Machine learning-based risk evaluations on all your card payments. | ✔ | ✔ |
| Overview of the machine learning engine. | ✔ | ✔ |
| Default rules for CVC and ZIP code verification. | ✔ | ✔ |
| Insights on the latest state of your fraud prevention, with metrics on your rules performance, manual review efficiency, and fraud activity. | ✔ | |
| Rules to automate custom business logic. | ✔ | |
| Review workflows for suspicious payments. | ✔ | |
| Lists to automatically allow or block trusted or blacklisted customers. | ✔ | |
| A risk score (0–100) that gives you granular insight into the risk level of a card payment. | ✔ |
Requirements
To use Stripe Radar, your website or app must use Checkout, Stripe.js and Elements, or our mobile SDK integrations for iOS and Android when processing card payments. These methods for accepting payments allow Radar to collect information on anomalous device or user behavior that may be indicative of fraud.
You should ensure that your own privacy policy tells your customers about this type of collection. Here is a paragraph you could add to your policy if it does not already include such a disclosure:
Next steps
Read on to learn more about risk evaluations that appear in the Dashboard and API, best practices for reviewing payments, and how to maximize machine learning performance with your integration.