U.K.-based antifraud software provider Featurespace this week announced it is seeking global patents on technologies that underpin its solution.
The company said the first patent is for its Automated Deep Behavioral Networks—a deep neural network architecture of connections and updates that enables users to identify and prevent more fraud. The second patent is around the company’s Behavioral Anomaly Score, which it says identifies anomalies in individual customer behavior without having any prior knowledge of contextual high-risk behavior.
“Financial institutions around the world are experiencing fraud and account takeover at unprecedented levels, with some reports estimating this number at more than $40 billion last year,” said Dave Excell, founder of Featurespace. “The Automated Deep Behavioral Networks patent and associated technologies deliver the right levels of model performance the industry needs to decrease fraud and protect consumer accounts before attacks happen. Technology, specifically machine learning, will continue to be central in the fight against fraud.”
Featurespace’s technology grew out of research at Cambridge University.