Pay.UK and Visa have said their recently completed machine learning-driven fraud detection pilot has "exceeded expectations".

The pilot, which was also rolled out in collaboration with Synectics Solutions and Featurespace, detected over £112 million worth of fraud.

Pay.UK said the results show an average 40 per cent uplift in fraud detection at a 5:1 false positive rate.

The pilot was first confirmed in June 2023 when Pay.UK contracted industry partners to test the potential benefits of the service with a group of participating banks and payment service providers (PSPs).

It ran for three months, with each partner receiving historic Faster Payments transactional data from participating banks and PSPs under a "pioneering data-sharing agreement".

Each partner independently built machine learning models which identified suspicious activity and compared it to known fraudulent behaviours.

The pilot found that the new overlay service is successful in detecting fraudulent activity before it occurs.

"The positive results from this pilot demonstrate the importance of innovation and cross-industry collaboration in developing effective solutions to stay ahead of fraudsters and protect people in the ever-changing payments landscape," said Kate Frankish, chief business development officer and anti-fraud lead at Pay.UK. "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.”

Mandy Lamb, managing director of Visa UK & Ireland said that while the UK has one of the most developed payment systems in the world, it also sees some of the highest levels of account-to-account fraud.

"Once fraud happens, the money is in the hands of the criminals so fraud prevention must be our collective goal, in the financial services industry and beyond," added Lamb.

---