FICO launches algorithms to attack CNP fraud

At a time when millions of people in the United States are coming to grips with the fact that at least some of their personally identifiable information (PII) is now for sale on the Dark Web, good news on the security front is welcome. And Fair Isaac Corp. (FICO) just introduced machine learning algorithms that it said can boost card-not-present fraud (CNP) detection by 30 percent. Good news indeed.

It's true that widespread EMV (Europay, Mastercard and Visa) chip card implementation will make it extremely difficult for fraudsters to use counterfeit cards at the physical POS using PII stolen during the Equifax and other high-profile breaches, but that won't stop them from exploiting vulnerabilities in the CNP arena, which includes not only online, but also mobile wallet transactions.

"Consumer convenience is driving rapid growth in online transactions. As a result, criminals are looking to use this convenience to their advantage as chip cards and other security features have made physical card fraud more difficult," said TJ Horan, Vice President for Fraud Solutions at FICO. "Our goal is to help card issuers promote a positive consumer experience while protecting them from financial harm. These CNP machine learning innovations are important tools to help issuers spot fraud faster, and take on even greater importance in the light of recent data breaches, which will lead to more fraud attempts."

Machine learning innovations

According to FICO, its new Falcon Platform consortium models can help protect these transactions, because they include machine learning innovations that improve CNP fraud detection without increasing the false positive rate, a standard metric for fraud model performance; reduce CNP transaction review rates without increasing fraud risk; and double the detection of fraudulent, high-value CNP transactions on the first attempted transaction.

"Machine learning algorithms are greedy — they gobble up data," said Dr. Scott Zoldi, FICO's Chief Analytics Officer. "Fortunately, our unique Falcon consortium has rich, anonymized transaction data on billions of payment cards and merchants, allowing us to build and validate algorithms that represent deep behavioral patterns. In production, these learned highly predictive behavioral variables and profiles of cardholders and merchants are updated with each transaction, in real time, in order to identify and adapt to behavioral outliers."

FICO noted that the company holds more than 90 patents related to artificial intelligence (AI) and machine learning in fraud detection; it has applied AI-based behavioral analytics to detect fraudulent transactions for 25 years; and the FICO Falcon Platform protects more than 2.6 billion payment cards worldwide.

Editor's Note:

The Green Sheet Inc. is now a proud affiliate of Bankcard Life, a premier community that provides industry-leading training and resources for payment professionals. Click here for more information.

Notice to readers: These are archived articles. Contact names or information may be out of date. We regret any inconvenience.