New CA Risk Analytics incorporates neural network authentication to catch credit card fraud

CA Technologies has rolled out a new release of CA Risk Analytics which includes intelligent, self-learning authentication technologies that help reduce friction for consumers during online checkout and allow card issuers to reduce incidents of fraud, increase revenue and gain unprecedented flexibility and control in their fraud detection systems.

The latest version of CA Risk Analytics incorporates patent-pending behavioural neural network authentication models for assessing risk of online, card-not-present (CNP) transactions. The neural network models are powered by machine learning techniques that capture data about individual user actions and enable CA Risk Analytics to better understand and distinguish legitimate behavior from fraudulent behavior. Optimised for the 3-D Secure protocol, CA Risk Analytics prevents CNP fraud in 3-D Secure transactions by transparently assessing the risk of a transaction in real-time.

“History shows that the continued global rollout of the EMV standard and the increasing distribution of Chip and PIN cards will result in an increase of CNP fraud attempts. This demands a more advanced CNP fraud detection strategy that goes beyond just comparing the current transaction to established fraud indicators,” said Vic Mankotia, VP, solution strategy, Asia Pacific & Japan, CA Technologies. “CA Risk Analytics and its behavioural neural network models will result in 'zero touch' authentication that will instill a level of confidence and streamline the online checkout process.”

CA Risk Analytics considers both fraud patterns and legitimate transaction behavior and tracks the pivotal players in a transaction: card or device, for example. It estimates the risk of fraud using advanced machine learning techniques to understand normal behavior for these pivotal players as well as the fraud risk related to deviation from past behaviours. This results in a more accurate assessment of which transaction to authenticate and helps stop fraud in CNP transactions.

CA Risk Analytics adds key capabilities:

· Increased flexibility and control for the card issuer. 

Card issuers can instantly change score thresholds and policies at their discretion. This gives them more control over their business so they can adapt to market conditions, better handle staff fluctuations or deal with current events that may demand examining a higher or lower volume of transactions while still ranking the most risky first. Card issuers no longer have to rely on vendor-only control of their system settings.

· Reduced fraud with revenue and cost improvements. 

The neural network authentication models within CA Risk Analytics help improve the accuracy of detecting legitimate from fraudulent transactions. This helps to reduce fraud and increase revenue. Better accuracy in detection also helps manage the cost of transaction analysis.

· Better customer experience. 

Because the models in CA Risk Analytics can better detect legitimate customer behaviour, there is no need to add friction to the checkout process and challenge the consumer with additional authentication to prove their identity.