Featurespace launches Automated Deep Behavioral Networks for cards & payments

By Megha Bhattacharya

UK-based FinTech Featurespace today announced the launch of Automated Deep Behavioral Networks for the card and the payment industry. The new service aims to offer customers protection against scams, account takeover, card and payments fraud, etc. Automated Deep Behavioral Networks is a new architecture based on Recurrent Neural Networks that is available through the latest version of the ARIC Risk Hub.

“The significance of this development goes beyond the scope of addressing enterprise financial crime. It’s truly the next generation of machine learning,” said Dave Excell, founder of Featurespace.

According to Featurespace, the development of the Automated Deep Behavioral Networks aims to automate feature discovery and introduce memory cells with a native understanding of the significance of time in transaction flows, improving upon the performance of the company’s Adaptive Behavioural Analytics.

Excell continued, “As real-time payments, digital transformation and consumer demand require the instantaneous movement of money, our role is to ensure the industry has the best tools for protecting their organizations and consumers from financial crime. I am immensely proud of our research team and their dedication to machine learning innovation on behalf of our customers.”

Featurespace stated that the development will benefit customers by enabling genuine transactions with reduced verification as well as automatically identifying scams, account takeover, card and payment fraud attacks before the victim’s money leaves the account. Data scientists will be able to automatically discover features in transaction events, use the irregularity of human actions to identify anomalistic behaviour; and retain all of the discoveries of Featurespace’s Adaptive Behavioural Analytics.

Automated Deep Behavioral Networks aim to improve risk score certainty across all transactions, provide performance uplift for all payment types, improve detection of high-value and low-value fraud, reduce step-up authentication, provide strict model governance documentation and deliver stable, real-time scoring with high throughput and low latency response times for business-critical enterprises, even under surge conditions.