The ai Corporation believes its new group of self-service machine learning products will help banks fight the growing problem of ACH fraud.
The technology allows banks to establish their own rule sets within any fraud prevention platform. Via machine learning banks can automate their fraud prevention systems.
ai’s SmartScore uses artificial intelligence and automated machine learning to recognize fraud patterns and trends, and create neural models which in turn produce transaction risk scores to be used with user-defined rules and parameter mapping. Those neural models may be specific to unique fraud types, customer segments or payment methods.
Credit-based ACH payments such as direct deposit, payroll, person-to-person and vendor payments are now settled within one day. ACH debit-based payments will soon join that list.
The reduced time helps fraudsters as that leaves a smaller detection window. ACH-specific neural models are a response to this, ai said. Data visualization tools allow data (including larger sets) to be analyzed in greater detail. Through network visualization technology trends can be identified and similar investigations consolidated.
Southhampton and Leuven Universities have joined ai on the newly-created Research Council to assess the benefits of using true machine learning in fraud prevention. ai CTO and Research Council chair Tom Myles explains the new body’s goals.
“One of the team’s focuses will be the adoption of true machine deep learning. This is the movement away from supervised to an unsupervised self-learning system, with the purpose of fully automating fraud prevention activities for all payment types.
“Alongside our partners at Southampton and Leuven Universities, our focus will be to build on our view that fraud prevention platforms are capable of more than detecting fraud. We want to look at ways we can leverage ai’s technology to create solutions that can automate all manner of processes. Not just fraud prevention, but other areas of the business such as credit scoring, credit monitoring, gateway switching and interchange optimization. Ultimately, ai’s platform is a reusable technology asset that has a wider business application as an end-to-end decision engine.”