Stripe Launches Radar To Help Merchants Block Fraudulent Transactions
By Christine Kern, contributing writer
Retailers turning attention to preventing ecommerce fraud in wake of EMV transition.
To help its merchant customers block fraudulent transactions on its platform, online payments network Stripe is launching a new artificial intelligence-based e-commerce monitoring suite called Radar, according to TechCrunch.
In a test with a small group of customers that include crowdfunding nonprofit Watsi and custom T-shirt company Teespring, Watsi was able to block $40 million worth of attempted fraud, according to TechCrunch.
“Talk to any internet business and you’ll frequently hear that fraud is a huge pain in the neck for them,” asserted John Collison, Stripe’s cofounder. “Anyone trading or doing business online has this problem.”
Venture Beat explained that Stripe Radar is able to identify not only the frequency of a card’s usage, but also the normal user behavior, including IP addresses making the transactions. Stripe Radar will be able to tell businesses more detail regarding why a card is blocked for fraud to help merchants avoid missing out on sales for false negatives.
TechCrunch explained that the machine learning aspect of the fraud prevention suite was enabled in part by assigning values to every transaction in Stripe's history, which helped create a predictive model that can be used in determining the likelihood that a given transaction is fraud.
With the first anniversary of the EMV chip card transition now behind us, retailers are beginning to see reductions in in-store payment fraud, allowing the retail sector to turn its attention toward tackling the growing issue of e-commerce fraud. A study from Forter found that a 27 percent increase in e-commerce fraud between the fourth quarter last year and the first quarter this year, while a separate Experian study found that 2016 e-commerce fraud attacks were well on the way to surpassing 2015 totals by 15 percent.
Stripe Radar is currently being rolled out as part of its existing payment platform for no additional charge, though that may change in the future. “This is an area of active development and there is a long list of things we want to do,” explained Collision. “We haven’t ruled out [launching it as a separate service] but want to see how people use it and what works and what doesn’t first.”
And since retail e-commerce is projected to reach nearly $2 trillion globally this year alone, according to eMarketer estimates, with growth rates of more than 20 percent over the next two years, tackling e-commerce fraud is serious business. A survey conducted by Pymts and Forter found that in Q4 of 2015 there were 27 fraud attempts for every 1,000 transactions, and in Q1 2016, some $4.79 out of every $100 in transactions was at risk (a year before it was $2.90).
Ultimately, Collusion explained to TechCrunch, Stripe Radar works because it integrates human and artificial intelligence to combat fraud. “In chess, the best players are not computers nor humans but humans working with computers,” Collison offered as an analogy. “It’s a little bit like that. We have all the machine intelligence, building logic that helps you run your business.”