Payments technology provider ACI Worldwide has debuted its new Incremental Learning technology – a new approach to machine learning that it hopes will enhance fraud protection for merchants, financial institutions and their customers.
ACI has filed a patent application for its ‘Incremental Learning’ technology, which is being implemented in machine learning models within ACI’s fraud prevention solutions. This includes Proactive Risk Manager, which delivers enterprise fraud management capabilities for financial institutions and intermediaries, and ACI ReD Shield, which underpins ACI’s secure eCommerce and merchant fraud management capabilities.
ACI claims it’s Incremental Learning’ technology represents ‘a significant advancement’ over current machine learning models that need to be retrained as fraud patterns change. Incremental Learning models are able ‘to think for themselves’ and make small adjustments on an ongoing basis to ensure they remain relevant, even as fraudsters and genuine consumers change their behaviours, it says.
A series of tests, carried out over 13-months on data from three major retail customers, revealed that while traditionally trained models began to degrade after three months, ACI’s incremental models maintained their performance over the full period of the test.
“As fraudsters become more sophisticated, we need to continuously advance our models to beat them at their own game,” said Jimmy Hennessy, director of Data Science, ACI Worldwide. “Our global data science team has created a game-changing piece of machine learning technology that can be seamlessly integrated and future-proofs the precision and operational efficiency for over 5,000 institutions protected by our solutions today.”