Financial regulators in search of a solution to “de-risking” are starting to ask if artificial intelligence could be the answer.
The Financial Action Task Force (FATF) has noted that banks resort to de-risking due to out-dated legacy systems and a poor understanding of the relevant threats.
“This is where new technologies can provide the most added value”, the Financial Action Task Force (FATF) wrote in a recent report.
The practice of de-risking is mostly a response to anti-money laundering and countering terrorist financing (AML/CTF) obligations. It arises when banks refuse to do business with individual customers or even entire customer categories that they deem to be associated with higher AML/CTF risks.
Banks under scrutiny
Banks justify these types of decisions on various grounds, but such broad actions are now coming under scrutiny. In January 2022, the European Banking Authority (EBA) published an opinion on the scale and impact of de-risking, and called on national regulators to take further action.
In its opinion, the EBA noted that de-risking isn’t warranted under EU law and can be a sign of ineffective AML/CTF systems. Banks should manage these risks better rather than resorting to such crude measures.
Some regulators have acted swiftly. The National Bank of Belgium issued a circular in February reminding banks of their obligations to properly manage risks and forbidding them from excluding entire categories of customers.
The circular also clarifies that banks are free to charge higher prices to riskier customers to reflect the extra costs associated with added due diligence.
However, the problems may run deeper than a lack of basic due diligence, as FATF has pointed out. The traditional rules-based approach tends to be static, cannot analyse data at a large scale and rarely provides a real-time overview of risks, which is why banks resort to overly defensive, box-ticking practices such as de-risking.
Solutions powered by artificial intelligence and machine learning could be the answer to the need for more granular insights. Such approaches allow banks to identify, assess and manage AML/CTF risks much more efficiently, as well as enabling a richer level of analysis and insights.
As regulators take the impacts of de-risking more seriously, it may only be a matter of time before they require banks to adopt new technologies to improve their management of AML/CTF risks.
In Europe, the EBA sees de-risking as a threat to the EU’s financial inclusion goals and is also worried about anti-competitive effects.
As the FATF states, individuals affected by de-risking are often from vulnerable, minority backgrounds, such as asylum seekers from countries associated with AML/CFT risks. Excluding such individuals from access to basic banking services raises human rights concerns and may have unintended consequences that increase AML/CFT risks.
De-risking may also conflict with EU laws requiring banks to provide objective, non-discriminatory and proportionate access to payments institutions, which are a common target of de-risking.technologies to improve their management of AML/CTF risks.
De-risking may also conflict with EU laws requiring banks to provide objective, non-discriminatory and proportionate access to payments institutions, which are a common target of de-risking.
Banks that are moving proactively to embed machine learning and artificial intelligence into their monitoring frameworks are well placed to benefit. Addressing the inadequacies that lead to de-risking can ultimately lead to a more accessible and fair banking system and free up compliance resources that can be put to better use.
Want to know more about how Sygno’s AutoML solution can increase protection and drastically reduce false positives of your existing monitoring system?
Get in touch and we’ll be happy to discuss solutions.