Press Room

Advanced AI Helps Banks Predict when APP Scams are in progress

Trials with two major UK banks see a 120% increase in prevention of complex online banking scams


LONDON — LexisNexis® Risk Solutions today announces it has combined artificial intelligence with a host of complex fraud signals to more confidently predict when an online banking user is about to send a payment to a fraudster.

Trials with two major UK banks achieved a huge 120% increase in detection of in-progress Authorised Push Payment (APP) fraud among online banking customers. It also resulted in a 90% increase in the monetary value of fraud prevented and saw false positive rates more than halve – meaning less disruption for genuine payments.

Authorised push payment (APP) fraud is extremely complex for banks to detect and prevent, with losses totalling almost £250 million1 in the first half of 2022 alone.

To help banks tackle this problem, analytics experts at LexisNexis Risk Solutions turned to two previously untapped data sources – Live Call data and Global Beneficiary Information – to provide additional insights that can help fraud teams spot potential fraudulent behaviour in customer transactions.    

Live Call data tells banks that their customer is speaking to someone on the phone whilst making a mobile banking payment by analysing the user’s device activity. Analysis shows that one in four (25%) APP scams involve a live call, making this intelligence extremely useful in fraud prevention strategies adopted by Banks. Global Beneficiary Information can help detect when a customer is trying to pay into a fraudster’s bank account by assessing any suspicious activity associated with the destination account across the global LexisNexis® Digital Identity Network® of user behaviour.

Combining these two data sources with a range of other complex fraud signals and the advanced machine learning capability of LexisNexis® Threatmetrix®, the team were able to successfully build and deploy fraud models that can help banks more reliably predict when an APP scam is underway.

Director of Analytics at LexisNexis Risk Solutions, Oskar Wismierski, says: “much anti-fraud technology builds trust on a limited number of factors, such as passwords and information about the device they’re using to login. This makes APP fraud particularly difficult for banks to spot whilst in progress, because it’s the genuine account user who logs in and makes the payment.

“Using the advanced modelling capability of Threatmetrix® to combine intelligence from Live Call data and Beneficiary Account behaviour with other device and location intelligence, we’ve shown that potential scam activity can be predicted with a high rate of confidence and stopped before the money ever leaves the victim’s account.

“These actionable insights could give UK banks a significant advantage in the ongoing fight against UK fraud that costs victims hundreds of millions of Pounds a year.”

About LexisNexis Risk Solutions

LexisNexis® Risk Solutions harnesses the power of data, sophisticated analytics platforms and technology solutions to provide insights that help businesses across multiple industries and governmental entities reduce risk and improve decisions to benefit people around the globe. Headquartered in metro Atlanta, Georgia, we have offices throughout the world and are part of RELX (LSE: REL/NYSE: RELX), a global provider of information-based analytics and decision tools for professional and business customers. For more information, please visit. For more information, please visit LexisNexis Risk Solutions and RELX.

1UK Finance Annual Fraud Report, 2022, UK Finance
Media Contact Form

Media Contacts

Mike Normansell
Senior PR Manager
+44 73 7715 2610