Bank Fraud

Pay.UK hails fraud detection pilot results


Pay.UK says a fraud detection pilot involving Visa has exceed expectations, suggesting that it could save the country’s economy over £112 million a year.

APP fraud has quickly become one of the most significant types of fraud in the UK, with losses totalling around £500 million last year.

Pay.UK – which runs the UK’s national retail payments system – ran the three month pilot with Visa, Synectics Solutions, Featurespace and a group of banks and PSPs.

The initiative trialled a new overlay service which will allow all UK banks and building societies to analyse money flows and use predictive intelligence to detect fraud and help prevent crime before it occurs.

Tech partners received historic Faster Payments transactional data from participating banks and PSPs under a data-sharing agreement. Each independently built machine learning models which identified suspicious activity and compared it to known fraudulent behaviours.

The pilot saw an average 40% uplift in fraud detection at a 5:1 false positive rate. This would see over £112m worth of fraud detected in a year.

Visa says its AI tool correctly identified an additional 54% of fraud and APP scams beyond those spotted by the banks’ prevention systems. The US giant claims its real-time fraud detection service could potentially help save the UK economy over £330 million a year.

Pay.UK says the tool has been designed so that is can be adopted by all PSPs.

Kate Frankish, chief business development officer and anti-fraud lead, Pay.UK, says: “In 2023, the UK saw 232,429 people falling victim to fraud. To reduce the scale of the crime that is happening we need a unified approach, and this future service will be a major step forward.”

Discover new challenges and opportunities artificial intelligence brings to the banking sector at Finextra’s first NextGenAI conference on November 26 2024. Register your interest here.


Read More

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button