Throughout the banking and payments industries, including recently at Money2020 Copenhagen, we’re hearing increasing pressure on merchants and financial organisations to achieve increased card acceptance while causing minimal customer friction.
This challenge is made even harder with rising fraud levels and evolving data breaches; the National Audit Office recently reported that over GBP 150 billion was lost to fraud in 2016, with cyber-related fraud accounting for 16% of all reported incidents.
Searching for a quick fix against rising fraud losses, many organisations add steps to the customer authentication process. However, shifting the security emphasis (and work) to the customer achieves the opposite of growing customer satisfaction and improving the usability of a purchasing portal. Adding more security steps is inconvenient for the customer and it is more likely to lose them before they complete a transaction.
Having worked inside fraud operations, I have seen first-hand that more layers of authentication can complicate fraud management and increase costs, instead of streamlining processes, especially if the underlying models and customer information gained are not properly managed.
What are the roadblocks to achieving customer satisfaction?
Authentication is one issue to tackle. We are also hearing from card issuers, acquirers, and merchants that they are experiencing other key barriers in proactively reducing customer friction, including that:
- Many legacy fraud models do not analyse events in context, such as comparing an individual’s behaviour to the behaviour of their peers. These fraud systems do not look at the bigger picture that contextual data can offer (for example, about current events or wider fraud or shopping trends), increasing the likelihood of genuine transactions being blocked.
- Authentication is often used as a rigid system, instead of taking a more individual approach which combines information on current risk levels with an individual’s behaviour. By not considering individual behaviour, adding authentication steps can add unnecessary friction for a large portion of a customer base.
How can fraud teams go beyond authentication to satisfy and protect customers?
The good news is that the latest machine learning technology is enabling financial organisations – and their merchants – to understand their individual customers in real time and gain control over reducing customer friction.
A real-time, machine learning fraud system which uses unique Adaptive Behavioural Analytics understands each customer’s behaviour and automatically adjusts fraud prevention tactics, without the need for rigid thresholds and rules.
The self-learning nature of a machine learning system means that it automatically adapts and updates as behaviour changes are identified, giving financial organisations and merchants a proactive approach to significantly improving card acceptance while spotting and blocking fraud in real-time.
This modern technology enables fraud teams to get a view of the customer at both a global and an individual level, bringing data from many sources together to be proactive and flexible in protecting customers.
Defeating the fraud beast – and keeping the customer happy
Beating the fraud beast is an ongoing fight. However, having the right tools to tackle the fight enables fraud operations teams to use the best defence available without adding friction to the transaction process. In the fight against fraud, a proactive approach can help you stay one step ahead of the many-headed fraud beast.
About Luke Reynolds
Luke Reynolds is Chief Product Officer at Featurespace and has worked in the fraud management industry for over 25 years. Prior to joining Featurespace, Luke held roles in fraud and security operations in the banking and payments industry, including Callcredit’s Commercial Director of Fraud and ID and Lloyds Banking Group (head of retail audit, head of fraud, and head of group security and investigation). Luke also worked in fraud management at the UK Card Association and NatWest.
About Feauturespace
Feauturespace is a company that brings new insights through new ways of treating data. The company’s technology is deployed on-premise or via secure cloud in over 180 countries. Their ARIC (adaptive, real-time, individual, change-identification) platform uses Bayesian statistics to model and predict individual behaviour in real-time. This machine learning allows computers to understand when an individual customer’s behaviour is out of character and automatically evaluate risk.
Every day we send out a free e-mail with the most important headlines of the last 24 hours.
Subscribe now