With David Griffiths, Director of Regulatory Affairs, Eventus
How has the current alert-based approach to monitoring AML transactions evolved and what are its limitations?
That hasn’t changed much since the fight against money laundering became prominent around 2002, when the Patriot Act required banks to invest heavily in AML programs. In the market today, people still talk about knowing your customer (KYC), having a risk score on the customer and putting that in an alert that says, “If X is greater than Y, then alert. “…it’s transaction monitoring today.
It’s quite procedural. A bank may have hundreds of thousands of alerts generated per month, triggered by a transaction from a high-risk jurisdiction or individual, or a third transaction just below $10,000. You need an army of people to go through these alerts. For example, a bank’s monitoring tool might provide an alert for every transaction in a high-risk jurisdiction, or for an individual who requires enhanced monitoring, or if a transaction is the third transaction just below 10,000. $. Today some companies are using machine learning to reduce alert noise, but it’s still the contextless alert itself that’s the problem, because when you generate an alert, it has to be investigated – no if, of and or but.
And because banks have different businesses – retail banking, correspondent banking, private banking, all with different trade flows, trade flows, and transaction flows – it is difficult for transaction monitoring alert logic traditional to modify the logic of the parameters to take into account the differences in these flows.
What is a signals-based approach to monitoring AML transactions?
The monitoring of AML transactions is a complex discipline, dependent on the processing and filtering of masses of data, which themselves are constantly changing and increasing according to the demands of regulators and the methodology of bad actors. A signals-based approach leverages technology to enable customization and customization of alerts, which in turn addresses the market’s longstanding need for greater agility and efficiency in monitoring AML transactions.
With a seamless approach to deployment and service, enterprises can achieve efficiency, scalability and flexibility – putting control, with no additional overhead, in the hands of the monitoring team as they do face the challenges of today and look forward to the challenges to come.
What are the benefits of a signal-based approach?
A signals-based approach allows you to be more precise. With this technology-based approach, if someone has made a third transaction that’s just under the radar, you can choose whether you want to treat it as its own alert, or whether you want to combine it into a macro alert, generated by several signals. specific to that location or type of customer. With this approach, you have the ability to add context from benchmarks, such as external customer risk attributes, but the signal itself is also a customer risk indicator, which also improves KYC .
Standard alerts can be slow and inefficient. You can add AI or machine learning to reduce noise and false positives in these alerts, but AI and machine learning require vigilance in training and retraining models. It becomes even more complex in a world where banks and trade flows can be very different. A signals-based approach is a paradigm shift in how people handle AML transaction monitoring, i.e. through a system that can take multiple inputs and produce a single alert.
Signals are smarter and more effective because the approach is more specific and tailored to your business than a generic risk model. A signals-based approach allows for a higher level of transaction-level risk capture based on trade flows, compared to simply factoring in a KYC risk score that someone else has done. .
What are the specific applications of a signal-based approach?
At Eventus, we work a lot with crypto companies. Some companies generate a risk score for a particular portfolio, but what doesn’t exist right now is this feedback loop where transactions, trading activity, feed back into that score. A fundamental aspect of AML and KYC is enhanced due diligence, where customer risk is reassessed continuously, perhaps once or twice a year – you can’t really do this more frequently due to the volume of data. alert. But by being able to generate a signal, in addition to improving alert generation, these signals can improve enhanced due diligence in a faster way.
For the past 20 years, there has been a standard list of alerts that everyone runs. The ability to create your own risk type or alert type provides much more flexibility based on specific types of customers, businesses and banks. This flexibility will lead to improved alert generation, better risk models, and improved turnaround times and conversion rates.
Is a signals-based approach more of a “tomorrow” story?
People have wanted a signals-based approach for years.
The point of this paradigm shift is to change the way you assess risk. This will not happen overnight, as an AML cycle within an institution typically lasts around five years. But in seven to ten years, I expect a signals-based approach to be much more prevalent.
What are the prospects for adoption in Asia specifically?
‘Explainability’ is the key. When you start talking about artificial intelligence and machine learning, people think it’s a black box – compliance people will be looking to make sure they understand how it works.
A signals-based approach to AML and KYC is not a new type of AI or machine learning. It’s a different way of thinking about how you achieve the end goal of identifying your risk. There’s nothing “funky” about it. We are not changing KYC – we are improving transaction monitoring capability by allowing you to create your own alerts.