A company founded by an Indiana University graduate to fight payment-card fraud with data analytics, statistical modeling, and Machine Learning is now backed by the school’s Innovate Indiana Fund. Part of a $2.6 million investment round, the funding will help Chicago-based Rippleshot launch a new product later this year aimed at stopping criminals from scamming online merchants.
The company—founded in 2013 by IU alumus Yueyu Fu, Canh Tran, and Randal Cox, who have a combined 40 years of experience working in financial services and fraud detection—is going after a market expected to total more than $183 billion between 2015 and 2020, according to payments industry newsletter The Nilson Report.
Kaleigh Simmons, Rippleshot’s marketing director, says that a few years ago, the company’s founders noticed a dramatic rise in credit and debit card fraud, and they wanted to try using big data technologies to proactively mitigate the problem.
Tran, the CEO, is a fly-fishing enthusiast who chose the company’s name because it refers to the ripple across the water that a fish makes when it comes to the surface, indicating that it’s going to bite the lure. (He viewed the company’s ability to identify the early ripples of fraud in a similar way, Simmons says.)
Rippleshot’s cloud-based technology can identify in real time where and when payment card information is being stolen by analyzing transaction data submitted to the company by financial institutions, Simmons explains. Once fraud is detected, the company advises its customers (financial institutions and merchants) on strategies to prevent losses.
“Every time we sign a bank up as a customer, we get all of their transaction data including disputed charges,” she adds. “Disputed charges are often an early signal that something is wrong.”
For example, say the Xconomy Detroit/Ann Arbor staff goes out for coffee, and a skimmer at the cash register picks up our credit card information. Even though we all have accounts at different banks, Rippleshot would be able to perform an analysis marking the coffee shop as the point of compromise and, using customer data from the time period during which the theft occurred, assign each customer a risk score.
