Whitepaper – Utilising Artificial Intelligence to prevent payment card fraud

Until now, the use of true machine learning to fight payment card fraud has been limited. Yet, we need it. With the total annual value of fraudulent transactions across Europe hitting €1.8 billion, the need to step up fraud prevention has never been greater.

Nets, a European payment services provider, has collaborated with multinational professional services provider, KPMG, to develop Nets Fraud Ensemble, a next-generation fraud monitoring and prevention solution. The impact of the solution resulted in an immediate fraud reduction of 25% and an estimated 40% long-term potential.

New paper reviews how financial institutions can harness advances in AI and machine learning to combat card fraud.​ Man and machine are the perfect pair when it comes to fighting payment fraud, according to a new whitepaper from European payments industry leader, Nets and multinational professional services provider, KPMG. 

Fighting Fraud with a Model of Models  explains how utilising human expertise in combination with artificial intelligence (AI) and machine learning (ML) technologies can significantly increase the accuracy of fraud prevention services. 

„Fighting Fraud with a Model of Models explores the theoretical approach behind Nets Fraud Ensemble, an AI-powered anti-fraud engine developed in collaboration with KPMG, which can reduce fraudulent transactions by up to 40% on top of existing AI fraud prevention measures.”, according to the press release.

Sune Gabelgård, Head of Digital Fraud, Intelligence & Research, Nets, comments: “It’s time for financial institutions to stop playing catch-up with fraudsters and, instead, get ahead of the curve. The business of fraud prevention has become increasingly convoluted, with the mass adoption of e-commerce, increases in cross-border payments, and the growing popularity of new digital payment methods all adding new layers of complexity. Humans cannot tackle these challenges alone. Until now, the use of true machine learning to fight payment card fraud has been limited. We need it now. There are patterns in the data which are hugely valuable in the fight against fraud, but that are too complex for the human brain to identify. Machine learning can not only find these, it can analyse and act on them too and prevent fraudulent transactions.”

Bent Dalager, Nordic Head of NewTech and Financial Services, KPMG, adds: “We have applied an innovative machine learning approach utilizing several machine models in unison. This approach has a clear advantage and generates the most accurate fraud screening. When applied, this next level of fraud monitoring and prevention means banks and merchants can take a big step forward. Not only does it combat crime, it also improves the customer experience and dramatically reduces financial losses.”

„The ‘brain’ of Nets Fraud Ensemble consists of multiple models working together to analyse each individual transaction within ten milliseconds – the time frame in which a transaction can be safely blocked. The solution learns from the results of its analysis and adjusts accordingly, meaning the longer that it is operational the more fraudulent transactions are blocked, and the fewer false positives are granted.”, the companies said.

Fighting Fraud with a Model of Models  is available to download free of charge from the Nets website here.

The European fraud landscape

With the total annual value of fraudulent transactions across Europe hitting €1.8 billion, the need to step up fraud prevention has never been greater.

Card not present fraud now represents almost 80% of the total volume of fraudulent card transactions across Europe.

UK banks and card companies prevented £1.66 billion in unauthorised fraud in 2018 alone. This represents incidents that were detected and prevented by firms and is equivalent to £2 in every £3 of attempted fraud being stopped.