July 18, 2016

How is machine learning transforming payment protection?

Luke Reynolds, Fraud Director, explains to The Paypers the main benefits of using Adaptive Behavioural Analytics within a deep machine learning system such as our ARIC Engine to transform payment protection in financial services.

Luke outlines that Adaptive Behavioural Analytics can not only spot new and unknown types of fraud, but will then also automatically adapt the algorithms, making it a future-proof system. In comparison, rules-based systems use pattern-matching against known fraud types, which is not as accurate and requires constant re-tuning and updating following new fraud attacks.

The ARIC Engine, by understanding individual customers behaviour in context, can more accurately spot fraud occurring in real-time and reduce the number of genuine customers being blocked, ultimately improving revenue and reducing customer friction. Automating the analysis of complex, varied streams of data, allows companies to make faster, more accurate decisions about an individual customer, compared to relying on human analysis alone.

The largest payments processor in the United States, TSYS, partnered with Featurespace in order to strengthen its position in faster payments using machine learning, to provide clients with actionable insights in real-time, using adaptive behavioral analytics that result in operational efficiencies. Andrew Mathieson, group executive, issuer product group at TSYS explains that this technology provides “a sharp contrast to the industry paradigm of blocking more valid transactions in order to detect actual fraudulent activity.”

Read the full article on The Paypers website.