Sign up for The Paypers newsletter Follow The Paypers on LinkedIn Follow The Paypers on Twitter Follow The Paypers on Facebook Follow The Paypers on Google +
The Paypers, paypers, Insight in payments, News, Reports, Events
 advertisement
Expert opinion

Tackling fraud trends in 2018: what to expect and what your business can do to prepare

Thursday 8 February 2018 | 01:20 PM CET

New fraud tricks beat old security systems. Is machine learning the best option against fraud? Luke Reynolds, Chief Product Officer at Featurespace, says “yes”.

As we kick off 2018, businesses are looking for opportunities to protect and serve their customers while increasing revenues. Experience also tells us that a new year also comes with fresh risks and challenges to tackle to stay one step ahead of competitors. In the fraud prevention world, of course, we’re also trying to be one step ahead of the criminals. So how can businesses get an advantage and prepare for fraud trends in 2018.

What trends will fraud management teams need to tackle in 2018?

It is said that in the banking and payments industry, once again this year, there are both new fraud challenges to face and old fraud tricks to mitigate against.

So, which new areas need to be tackled to get ahead? What does your business need to do to become a fraud fighting customer champion?

Battle of the buzzwords – demystifying the hype

In 2017, AI and machine learning’s buzz dominated the financial world and will continue to be heard in 2018. The advantage for businesses in using AI can be found by sifting the ‘hype’ from the genuine real-time machine learning systems that can help protect and serve your customers by understanding individual customer behaviours.

With regulatory changes also coming this year, including PSD2 in the UK and Europe, more jargon-busting can be expected, especially when it comes to implementation.

Knowledge is power: how innovative data science technology can tackle payment fraud

With Card Not Present fraud and Authorisation Stream attacks on to rise, financial services organisations need to harness the power of data science when it comes to protecting customers. The most efficient, accurate way to do this is by identifying anomalies in real-time throughout the customer journey. Self-learning fraud prevention systems are key to keeping up with these constantly evolving fraud tactics.

Old tricks, new tricksters: customers and merchants are still at fraud risk

Apart from new fraud risks, the banking and payments industry is still vulnerable to existing fraud tricks, such as social engineering, where customers are manipulated via phone or email by criminals impersonating their bank.

As ecommerce fraud continues to rise, customers will keep getting caught in the crossfire between criminals and merchants who want to protect against consumer fraud and they may be falsely declined for online purchases. To get an advantage, businesses need fraud management systems that can identify their ‘good’ customers and block the criminals.

How to leapfrog ahead - what is the next step?

The good news? A fraud management solution for these challenges exists – and some of the world’s largest banking and payments companies are already getting ahead of the market by embracing it.

A real-time machine learning system which use unique Adaptive Behavioural Analytics gives fraud management teams the edge in the fight against fraud, by spotting behavioural anomalies and blocking fraud attacks as they occur. This software works by understanding individual behaviour in real-time and relying less on business rules that can be bypassed.

This approach is being used globally by banks, payments processors, merchant acquirers, insurers and gaming organisations to stop fraud, reduce customer friction and keep operational costs down.

  • Detect fraud as it happens: a machine learning software system spots and blocks fraud as it happens.

  • Reduce the number of genuine customer incorrectly blocked: using adaptive behavioural analytics, a machine learning approach monitors individual customer and merchant behaviours in real-time, enabling organisations to detect anomalies. The deep understanding of individual behaviour means that genuine activity can be identified more accurately, reducing the number of incorrectly blocked customers (also known as ‘false positives’).

  • Automatically improve fraud model accuracy: the most advanced of these fraud systems are self-learning. This means the fraud models do not degrade over time, unlike many legacy fraud systems.

Now is the time for businesses to get ahead of tackling the fraud trends for 2018. Whether it’s old or new fraud that you are faced with, the key is to use real-time machine learning to become a fraud fighting champion to protect and serve your customers.

About Luke Reynolds

Luke is Chief Product Officer at Featurespace, responsible for clients in Financial Services – discovering customer pain points and working with the engineering team to offer a solution via Featurespace’s ARIC™ platform. Prior to joining Featurespace, Luke worked in the Financial Services Sector for over 20 years. He held a position as Callcredit’s Commercial Director of Fraud and ID and served in a variety of roles in Lloyds Banking Group (Head of Retail Audit, Head of Fraud, and Head of Group Security and Investigation). Before joining Lloyds Banking Group, Luke held fraud prevention roles at the UK Card Association (formerly APACS) and NatWest.

 About Featurespace

Featurespace was created by a Cambridge University Professor and his PhD student, Dave Excell, at the forefront and confluence of two academic fields: Data Science and Computer Science. Featurespace built the world’s first Adaptive Behavioural Analytics engine – the ARIC platform – to solve this commercial challenge. We found the Financial Services industry was plagued by similar issues.

 advertisement
 advertisement
 advertisement
 advertisement