Featurespace Introduces Adaptive Behavioral Biometrics to Solve Complex Fraud Attacks in Digital Channels
June 03, 2019
From Money 20/20 Europe, Featurespace introduced Adaptive Behavioral Biometrics, which uses in-session behavioral data collected from digital channels in real time to detect and prevent fraud during customer onboarding and digital sessions.
Digital customer onboarding presents a significant challenge for banks, insurers, and other financial institutions because there is no historical information to accurately determine if an applicant is genuine or a criminal. These organizations are also bombarded with new threats to existing customers, such as malware, as well as account takeover and man-in-the-middle and phishing attacks.
Available through the ARIC Fraud Hub, Adaptive Behavioral Biometrics models track user-specific features collected ahead of a transaction. The models consistently self-learn from each interaction to produce a unique session fingerprint that indicates an individual user's usual or unusual behavior and provides fraud analysts with an easy-to-understand visual profile that even detects phishing and malware activity generated by genuine customers.
"We're attuned to the evolution of fraud and leverage our market-leading models and technology to continue to deliver the latest and most advanced fraud prevention and detection tools," said Martina King, CEO at Featurespace. “There has never been a more important time to support our customers in their drive to prevent fraud loss and reduce customer friction.”
About Featurespace - www.featurespace.com
Headquartered in the U.S. and U.K. and with offices in Atlanta, Cambridge and London, Featurespace™ is the world-leader in risk prevention and creator of the ARIC™ platform, a real-time AI machine learning software that risk scores events in more than 180 countries to prevent fraud and financial crime.
The ARIC platform combines unique Adaptive Behavioral Analytics and anomaly detection to automatically identify risk and catch new fraud attacks and suspicious activity in real-time. The increased accuracy of understanding 'good' behavior strikes the balance between improving the detection of suspicious activity, while also reducing the number of false alerts, to improve operational efficiencies.