The process of launching an effective ecommerce business can hold endless issues that should be taken into account. One of them is the possibility of fraud. Necessary protection can be rather expensive for small companies.
Radar is being rolled out globally as part of Stripe’s primary payments service. That means that companies using Stripe’s API for payments do not need to pay extra or do anything in particular to turn it on.
“Talk to any internet business and you’ll frequently hear that fraud is a huge pain in the neck for them,” explained John Collison, Stripe’s cofounder. “Anyone trading or doing business online has this problem.”
Collison underlined that nowadays there are many machine learning-based systems. However, it can be hard to understand what exactly they’re actually doing. And predefined rules and heuristics, such as implementing a blanket ban on prepaid cards if a few incidents of fraud are detected, are a bit of a blunt instrument. “There’s not a precise way to do this,” Collison said.
Stripe intends to help to companies by giving access to its network that is already supporting hundreds of thousands of businesses. Stripe’s database can replace the necessity to employ a team of data scientists who will be dealing with suspicious activity. It can provide loads of useful information – from the frequency of a card’s usage to the normal/abnormal behavior, the IP address that’s making the transaction and much more.
“We now have an enormous amount of data to bring to bear now that half of all Americans have bought from a Stripe-powered business,” Collison claimed.
Traditionally, the card is blocked when a fraud behavior is detected. But companies usually don’t understand what exactly has happened. Stripe Radar can be useful as it provides more details on the fraud. False positives – events where a card is declined for the wrong reason and as a result, the merchant misses out on a sale – are as bad as false negatives.
Stripe has created its Radar so that it fits into how merchants feel comfortable. Collison believes that Radar represents the first example of full integration of customization and machine learning into a fraud detection system. Managers of premium companies can instruct Stripe Radar to notify of suspicious transactions over a certain limit and require to contact the customer directly. Customers have an opportunity to decide how the system should respond to international transactions.
Stripe’s dashboard will also display the merchant’s dispute rate percentage as well as the number of high-risk payments Stripe blocked and the ones that were prevented because of established rules.