Insights

Understanding how bias can affect model development is important as AI tools are more broadly adopted.

Responsible AI is undoubtedly an important topic. As financial institutions adopt AI and machine learning across their operations, it’s important that these powerful tools are rolled out carefully to prevent biases from affecting model development.

However, some of the concerns around the use of AI reflect an unwarranted fear of the unknown. Bias is a risk in all models. Transaction monitoring is a case in point. Financial institutions that rely on traditional rules-based models often classify entire categories of risk to be too high to manage. This can lead to situations where high-risk sectors or countries are almost fully being excluded.

At Sygno, we believe that our approach has the power to broaden access to finance by enabling FIs to manage risks far more efficiently than is possible using conventional models.

“The main challenge lies in the fact that fraud or money laundering activity only accounts for 0.1% of the data, creating a very unbalanced situation,” says Sjoerd Slot, Sygno’s CEO. “As a consequence of the small number of data points, risk characteristics are typically defined rather rudimentarily and when applied to the larger population result in broad indicators that potentially lead to unethical biases.”

There are two approaches that can help FIs to reduce these biases in their fight against financial crime:

1. Focus on the 99.9% of non-fraudulent behavior, allowing for far more granular indicators.
2. Use explainable models that can be evaluated for the presence of potential biases.

This way AI becomes an enabler to lower bias and unwarranted financial exclusion.

Financial institutions can achieve quick wins in the TM parts of their compliance process – without waiting for larger IT projects to be delivered.

Delaying optimizations to transaction monitoring systems can be a costly mistake. Historically, it may have seemed sensible to time upgrades around other changes in the IT environment, to minimize complexity and avoid wasting investment as systems are changed. This approach is typically known as “getting the house in order before optimizing”. But there are compelling reasons to optimize TM frameworks sooner rather than later – even during such large IT change processes.

Money launderers and other financial criminals don’t wait for IT projects to be finished. They are constantly active and adopting more sophisticated techniques, which means that financial institutions relying on non-optimized systems face an ever-growing risk of regulatory breaches. Getting it wrong, while waiting for IT projects, can have significant financial, legal and reputational consequences.

The good news is that it’s now possible to optimize TM environments and leverage this for both the existing (old) environments, as well as the renewed TM system. With automated machine learning (AutoML), rulesets and detection models can be optimized much faster than most financial institutions might expect. Quick wins can be achieved in just a few weeks and with minimal disruption.

Indeed, AI-optimized AutoML solutions can even be implemented alongside existing TM systems, completely avoiding the need to wait for a major overhaul.

An additional advantage in optimizing the TM environment first or alongside IT changes is that it creates strategic technical and compliance capacity. Immediate compliance and efficiency gains can be achieved by reducing the overhead associated with traditional frameworks, such as handling the high volume of alerts and increasing detection ratios, as well as answering regulatory pressure for sound model risk management practices to be implemented. Such as above and below the line testing (ATL/BTL).

At Sygno, our clients generate their enhanced rulesets and models based on the behavior of their good customers. Our automated model generation solution can significantly optimize your TM environment, reducing the usual time and complexity.

With such solutions, there’s no need to wait a year or even more for the delivery of a large IT project. A “smaller” enhancement can achieve huge gains quickly, saving costs, freeing up resources, and reducing risks. And the optimization can easily be transported to the renewed TM environment or automatically re-generated in the new situation.

Getting started with optimizing your TM

Get in touch to find out how you can stop waiting and start optimizing your TM environment today.

Fintechs with smaller datasets can power-up their compliance processes with AI-driven solutions.

Big financial players have been investing heavily to deploy artificial intelligence (AI) in their anti-money laundering systems. From megabanks to fintech unicorns, compliance departments are increasingly taking advantage of machine learning (ML) and big data to improve their ability to detect financial crime.

Meanwhile, smaller fintechs and financial institutions struggle to implement similar anti-money laundering programs, despite often having a strong AI capability within their core product. This is mostly because AI in the risk and compliance domain requires not just technical expertise, but also significant domain knowledge.

The assumption is that bigger is always better for AI and ML tools – and that’s true in most cases. As the amount of data increases, so does the ability to recognize criminal patterns and develop insights. However, the size of your dataset doesn’t have to be a limiting factor when using AI/ML to optimize compliance processes. Focus on the data that you do have, rather than the data you don’t. Focus on the behavior of your good customers, where you have far more datapoints.

Custom models

Smaller fintechs often rely on off-the-shelf models or rules, that will never produce the best results for everyone. This may seem like the only cost-effective option for these players, but there’s a better way.

Even smaller fintechs can generate custom models on their data. By modeling the behavior of their good customers, automated model generation can help to recognize the relevant patterns even on their smaller datasets where there are fewer anomalies that indicate financial crime.

Size matters

While this kind of approach works well at any scale, it’s particularly effective for smaller teams that don’t have the resources to manage a complex solution.

Improving compliance and transaction monitoring processes at very large financial institutions can be a daunting task that may take years to fully complete, but for smaller players it can be done much more quickly.

In practice, it’s much easier for fintechs and smaller financial institutions to optimize their compliance processes. Smaller datasets, fewer legacy environments, and flatter management hierarchies tend to mean they are much more nimble organizations. And they want to maintain that agility.

Getting started with AI-optimized compliance

At Sygno, we’re building Automated Model Generation for regional and cooperative fintechs and smaller financial institutions, based on the patterns of their good customers. Which luckily is the majority of their data.

Did you know that you can turbocharge your Fraud and AML technology without a costly and time-consuming system replacement?

Getting better results from your transaction monitoring system doesn’t have to be a major headache. You can make big improvements without replacing or even upgrading your current system.

At Sygno, we’ve designed a software solution that plays nicely with other models. It can easily be integrated within your existing transaction monitoring engine and can generate its first model in a matter of hours.

No architectural changes are needed, which means that you can expect tangible results quickly. Full implementation can take as little as eight weeks, including your internal model validation time.

We can do this because our solution approaches transaction monitoring in a new way. Using automated machine learning to extract patterns of normal customer behavior, Sygno’s detection model is much better at spotting anomalies, which helps to reduce false positives and increase true positives.

It’s simple, but also effective. Unlike most Fraud and AML technology, Sygno can turbocharge your transaction monitoring without adding layers of complexity. We also provide our clients for each of their models a detailed report that explains exactly how our model was generated, which means your compliance team can easily present it to regulators.

The simplicity of our solution also means less workload for data scientists and case analysts. Freed from the burden of an unnecessarily complex system that generates too many false positives, they can focus on higher-value tasks.

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.

New technologies

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.

De-risking impacts

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.

Proactive response

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.

Managing huge (and growing) volumes of alerts is creating an avalanche of challenges for banks.

Transaction monitoring systems that produce a huge volume of alerts can be a big challenge for banks and other financial institutions. And the challenge is more than a simple matter of costs.

Let’s highlight some of the most serious adverse consequences:

One of the most fundamental issues is analyst retention. Nobody wakes up in the morning excited to slog through another day of exceedingly mundane and repetitive tasks with limited tangible results, but that is often the daily experience for analysts in the anti-money laundering area. Hiring and retaining good people for such roles is therefore tough. And retention of good analysts is important as the work requires skill and experience to verify these complex structures.

Closely associated with this is the issue of quality of investigations. It can be difficult to ensure that the quality of investigations is still sufficient when dealing with so many false positives due to analyst fatigue. The FCA has warned for years about poor practices that “generate large numbers of resource intensive false positives” and result in firms “discounting actual target matches incorrectly as false positives due to insufficient investigation”.

Which leads to the issue of missing crime. Catching real criminals is the core goal of transaction monitoring. When analysts are spending too much time on false positives, and financial institutions have to make choices about which cases to investigate, there’s a real risk that criminal activity will go undetected. This can lead to difficult conversations with regulators.

Last but not least, there is customer friction. False positives that block legitimate transactions are an obvious pain point for customers. Clients are also being asked to provide increasing amounts of information when being investigated. No businesses want to annoy their good customers for what are often clearly legitimate transactions, so there will always be pressure from the business to mitigate this. When prolonged, this may weaken support for otherwise understandable risk measures.

To make matters worse, the volume of alerts is only increasing and always at a faster pace than the resources available to cope with them.

Where to draw the line. You’ll never be able to do everything. And with so many challenges, it’s obvious that everybody wants to reduce the volume of false positives – while decreasing the risk of missing true positives.

There are no magic bullets

But there are better ways of managing the challenges. One of them is to focus on the expected behaviour of your good customers to catch the bad and reduce clear false positives.

Or as the SWIFT Institute recommended recently:

“Financial institutions should seek to monitor for consistency of client behaviours and report suspicion that arises, rather than seeking to find suspicious activity as a primary activity.”