FICO Wins Machine Learning Award for Scams Detection Model

Global analytics software provider FICO won the Machine Learning in Credit and Collections Award at the 2022 Credit & Collections Technology Awards, held in London in late November. The award was for an advanced scam detection model, which is available to lenders using the Retail Banking model in FICO®Falcon® Fraud Manager, the world’s leading payments fraud protection solution.

The proliferation of mobile payment apps, new open banking standards and consumer stress caused by the global pandemic have caused Authorized Push Payment (APP) scams to grow at an alarming rate. This financial crime occurs when a customer is manipulated into sending money to an account controlled by the scammer. In the UK alone, according to UK Finance, 2022 saw a 30% increase in APP scams, as compared to 2020, with losses totalling £249M in the six months measured in their October 2022 report. According to Javelin Strategy & Research, person-to-person (P2P) payment fraud grew 18% from 2020 to 2021 with an estimated 18 million Americans scammed using P2P applications.

“Scams fraud is difficult to identify because the payment is authorized by the customer, so you can’t detect it just by looking at traditional third-party fraud indicators,” said Scott Zoldi, chief analytics officer at FICO. “Using proprietary machine learning techniques, we developed unique features and specialized algorithms to identify this behavior and the likelihood of a scam in real time.”

The model was trained on data from the FICO® Falcon® Intelligence Network, a consortium of global payment data with more than 9,000 contributing institutions. The model scores payment transactions for the likelihood that they are authorized push payment fraud.

“One of Falcon’s key analytic weapons, the account’s behavior sorted lists (B-list), is used to help determine abnormality,” said Zoldi. “By monitoring key attributes of an individual’s payment history, B-lists learn customers’ frequent, repeated behaviors (i.e., “favorites”). Hits and misses on these favorites allow the Falcon Fraud Manager model to decide between fraud, scam, and normal behavior.”

While banks and card issuers today have used the Falcon Retail Banking fraud score to detect both fraud and scams, the new Scam Detection Score detects 50% more scam transactions at a 0.5% transaction review rate. When a customer is using a favourite device or computer, the new Scam Detection Score identifies 24x the number of scam transactions than a standard fraud detection model.

FICO Falcon Fraud Manager is the leading payments fraud solution, and protects more than 2.6 billion payment accounts worldwide.