Kount has announced that it is working with Fetch Rewards, a customer rewards application, to help protect its users’ accounts from hackers.
“People don’t know how valuable loyalty accounts are and how easy they are to monetize,” said Rich Stuppy, chief customer experience officer for Kount.
People who steal the accounts can sell them on online marketplaces, he said.
Fetch Rewards was particularly interested in Kount because Kount’s product, Kount Complete, uses artificial intelligence to help detect fraud, which they could automate, Stippy said. That means Fetch Rewards can limit its number of manual reviews, saving time for both the company and shoppers, and its customers can get their rewards more quickly, the companies said in a press release.
While other fraud detection systems also use artificial intelligence, the Omniscore feature in Kount Complete is more sophisticated than that in other fraud detection products.
What is Fetch Rewards?
Fetch Rewards, based in Madison, Wisconsin, is a mobile rewards application that provides shoppers with gift cards for scanning their grocery receipts, based on partnerships with brands such as KraftHeinz, Unilever, PepsiCo and KimberlyClark. It is agnostic, meaning that it is not associated with a single retailer.
Because the Fetch Rewards program rewards its customers with gift cards, that makes them more sought-after than are some other loyalty programs, Stippy said.
To date, Fetch Rewards shoppers have submitted more than 130,000,000 receipts and redeemed more than $22 million in rewards through using the application, said Peter Dermody, director of marketing, in an email message. Around 16,500 shoppers in Idaho have signed up for Fetch Rewards.
The company decided to look at a third-party authentication solution because it was seeing more fraud in the system, said Tyler Kennedy, vice president of operations. In addition, the company’s product had more users – 350% growth in the last six months.
“We currently receive over 500,000 receipts every day, and shoppers are redeeming hundreds of thousands of dollars in rewards every week,” Kennedy said in an email message. “With this growth, we began to see more users trying to circumvent our fraud rules. We were continually adapting to meet these new challenges, but it was a game of cat-and-mouse. We needed a way to get more information and make calculated decisions in blocking these users without impacting the experience of legitimate good users.”
Fetch Rewards approached Kount because it had a more robust solution and was more interested in forming a strong partnership than its competitors, Kennedy said.
This isn’t the first time Kount has partnered with a loyalty program, Stippy said.
“We do quite a lot with loyalty-type companies for individual brands, as well as platforms that provide loyalty and gift cards,” he said.
However, this is the first time that Kount has partnered with an individual grocery rewards application, he said.
Kount has always used artificial intelligence, or machine learning, to analyze the potential of fraud in a given transaction. The software does this in two ways: Supervised and unsupervised. In supervised machine learning, a human teaches the software how to recognize fraud. In unsupervised machine learning, the software goes back and analyzes Kount’s 12 years of transactions to learn how to recognize fraud on its own.
Previously, these two scores were used separately. Omniscore combines the two scores for a result that the company said is up to twice as accurate as previous scores. Because the score is more accurate, it means that merchants can hire fewer fraud analysts, she said.
In addition, Kount Complete has a policy engine that lets its customers set custom risk thresholds and drive business outcomes including a higher acceptance rate, lower manual review rate, fewer chargebacks and lower operational costs, the company said.
Kount Complete has 6,500 customers worldwide.