Stripe Radar 2.0

Improved fraud prevention with Radar 2.0

We launched Radar in 2016 to help protect our users from fraud. We’ve continuously invested in our fraud prevention tools, we’re excited to launch the result of those efforts.

We’ve also honed features to be even more useful to fraud professionals, built new features, and packaged them all together in a new bundle called Radar for Fraud Teams.

Around the web

Reviews

 
  • Pros: 

    The machine learning and the custom rules feature make it super simple to reduce the volume of fraud activity.

    Cons: 

    I don't have anything in my mind.

    Radar can help you predict fraud before purchase via machine learning. Since than we don't have to watch the transactions like a hawk, it's automatic and working like a charm. We were able to reduce the fraud signups by 98%. You can read more here https://kinsta.com/blog/credit-card-fraud-stripe/

    Tom Zsomborgi has used this product for one year.

Discussion

You need to become a Contributor to join the discussion - Find out how.
Ryan CroweMakerHiring@doctorcrowe · Social Media Communications, Stripe
Hey gang! We're here ready to answer any questions you might have about Radar. Let us know what you think.
Riegie Jeyaranchen@riegiegodwin · COO, Crown Labs Agency
Looking forward to the 2.0 version. The previous version of Radar has been a bittersweet experience for us. We had a lot of false positives processing transactions on site at events. When we looked into the dashboard, we saw that Stripe halted these transactions and flagged them as fraudulent. When we looked further into the cards being used and tested them, they were completely fine. A lot of customers complained. Just wondering, what are some of the parameters Stripe uses to determine whether a payment/card is fraudulent and how accurate is it? Thanks!
Michael ManapatMaker@mlmanapat · Engineering Manager, Stripe
@riegiegodwin I’m really sorry that you ran into this and I’m happy to chat about your specific business if you email me at mlm@stripe.com. To add a bit more color: We use thousands of signals to determine the risk level of a payment. (A random set of examples: how many payments we’ve seen on the card in the Stripe network, the distance between the IP address and billing address, whether the same device was used to make other payments using different cards, and so forth.) With all that said, the new Radar for Fraud Teams features should also be able to help here: - You can disable the default rules and mark transactions as safe if you write in to support@stripe.com (so if Radar incorrectly blocked a payment, you could mark it as safe and subsequent payments would be allowed). - You can customize the threshold at which Radar blocks charges—so if false positives are very costly for your business (because you have large margins, e.g.), you can tune Radar to reflect that; you can also specify lists of trusted payment attributes to “allow” (if you have known good card numbers, e-mail addresses, IPs, etc.)