Payments fraud is growing at 14% year over year, faster than overall retail sales, and growth in mobile fraud is also accelerating. According to Juniper Research, retailers could lose as much as $130 billion between 2018 and 2023, reaching $7.2B by the year 2020.
Fraud protection firm Kount has launched a next-generation artificial intelligence (AI) platform that could be an effective new weapon to combat the dramatic growth of payments fraud.
How does AI fraud analysis work?
Experienced fraud analysts look at a company’s historical data, search for fraud patterns and anomalies, and assess the risk and safety of transactions to set risk tolerance levels for business.
Kount AI simulates the decision-making process of a skilled fraud analyst, resulting in a faster, more accurate fraud protection solution.
The company uses supervised machine learning, built on analysis from Kount’s universal data network that includes billions of transactions over 12 years for 6,500 customers in more than 180 countries, and taking place on multiple payment networks.
The result is an unsupervised AI fraud protection program that employs advanced algorithms and models to detect anomalies much faster, more accurately, and on a more scalable level than human analysis alone.
“The supervised machine learning aspect of Omniscore reflects the historical experience that seasoned fraud analysts possess, while the unsupervised features simulate the instinct or ‘spidey sense’ of the very best analysts to detect that a new type of attack is underway,” said Tricia Phillips, Kount’s SVP of Product and Strategy.
“More than any other model we’ve seen, Omniscore truly behaves as a human would in the risk assessment of a payment transaction, which is the very definition of artificial intelligence,” Phillips said.
Fraud protection ROI
US new account fraud losses grew to $3.4B in 2018 from $3B in 2017 and in 2018, 1.25% of US consumers were a victim of new account fraud, caused by criminals using consumer information to open a fake account. It’s a challenging problem because new account fraud doesn’t require payment information initially.
Kount AI quickly and accurately detects existing or emerging, automated, and complex fraud providing the control companies need to protect against fraud and meet other business objectives, such as balancing chargeback rates, decline rates, and monitoring operational costs.
“The ability to quickly identify complex and emerging fraud patterns by Kount’s new AI solution, along with customizable controls for the business, will play an important role in allowing businesses to achieve their financial goals without sacrificing customer experience,” said Steven D’Alfonso, Research Director with IDC Financial Insights.
In 2018, consumers lost a reported $488 million through data breaches, according to the Identity Theft Resource Center. That shows cybercriminals are forever adapting and looking for the newest fraud opportunities.
As long as fraudsters don’t implement their own artificial intelligence weapons, fraud protection could be significantly enhanced as Kount and other fintechs start applying AI to combat the growing problem of payments fraud.