ID Finance adds behavioral biometrics to its AI-based fraud scoring engine
Fintech firm ID Finance is incorporating behavioral biometrics into its AI-based fraud scoring engine to eliminate fraud, boost loan approvals and reduce the incidence of non-performing loans.
According to the announcement, the behavioral biometrics system was developed in-house by ID Finance’s team of data scientists, risk analysts and developers. The pilot program reportedly operated at an accuracy level of 97.6 per cent and has now been rolled out to all seven markets of operation. Over time ID Finance expects the accuracy level to increase as the system gathers more data and continues to learn about its users.
The system studies the unique typing and behavioral patterns users display during the loan application process to capture a range of patterns including mouse movements and keyboard interaction and records patterns such typing speed, typos, flight time between keys, keystroke depressions, as well as the patterns from actual input.
“The six-month pilot of our behavioral biometrics system has shown enormous potential,” said Chief Risk Officer Ekaterina Kazak. “Any deviation from normal usage patterns will raise a red flag even if a user’s password and username have been input correctly. Behavior patterns cannot be faked and behavioral biometrics offers one of the strongest forms of authentication. We are even considering replacing user passwords with this data.”
ID Finance is working to develop the technology to cover mobile keypads and touchscreen devices. It will capture patterns on such as the amount of pressure applied to the screen and how quickly fingers swipe and type.
In a reecent interview with Biometric Update, BioCatch VP Frances Zalazny said that behavioral biometrics are the wave of the future.