Published 21st July 2016

Machine learning fraud detection systems could save card issuers and banks $12bn annually

In a study published in conjuction with portfolio company featurespace, Oakhall, the London based analysis firm, estimates that global financial services firms could save at least $12 billion annually by employing adaptive, machine learning fraud management systems.

Adaptive behavioural analytics software could increase the identification of actual fraudulent transactions by 25%, and reduce the number of ‘genuine transactions declined’ by more than 70% (which would also reduce the costs associated with managing blocked customers). This change in could save the industry over $12 billion from its $31 billion total annual cost of card fraud.

Martina King, Featurespace CEO, commented:

“Having genuine transactions declined is extremely frustrating for consumers and damages their relationship with the card issuer or bank. They also result in lost revenue and substantial costs to the bank.

“Data-driven adaptive behavioural analytics – delivered via the ARIC engine – protects bank revenues and substantially cuts operational costs from false fraud alerts. It also helps the banks maintain positive relationships with their customers.

“The leading US payments processor, TSYS, chose to provide ARIC to its customers because of ARIC’s enhanced machine learning capabilities and decision-making around fraud and genuine transaction activity.”

Learn more about the report and Featurespace

Download the full study