Using AI and machine learning to fight money laundering

Data scientists have done a great deal for us in the way of making our financial lives easier and, without a doubt, more secure than ever before. These advancements aren’t always used for good, however. While technology has brought the financial world forward in leaps and bounds, it’s worth remembering that this same technology is used for far more nefarious reasons: cybercrime in its many forms.

The Cost Of Money Laundering

Fighting money laundering is a massive, costly mission that needs to be perpetually in motion. For context, anti-money laundering (AML) measures cost European banks roughly €18 billion each year, with their US counterparts shelling out approximately €22 billion annually.

Banks all over the globe need to have their fingers firmly on the pulse of the fintech ecosystem, and that means paying close attention to their transaction monitoring standards. Failure to do so could leave banks with a hefty fine. The last ten years have seen a whopping 90% of Europe’s banks slapped with fines for failing to take the required AML measures – that’s €23 billion on fines alone.

Changes in the tech landscape

Staying at the forefront of tech is crucial for any organisation hoping to remain relevant in a highly competitive industry. AI and machine learning are developing at breakneck speed, with the biggest cloud providers in the industry making them a clear priority over the last few years.

This tech has the potential to completely revolutionise the front and back-end operations of financial bodies across the globe, boosting risk management efforts, maximising efficiency, and reinforcing the effectiveness of financial crime investigations across the board. Embracing this new tech can also minimise costs by helping financial institutions meet regulations more efficiently, freeing up human resources that can be assigned to other vital areas of the business in the process.

Types of AI and machine learning

There are two types of AI and machine learning, each with its own set of pros and cons – supervised and unsupervised. Supervised learning involves using a model trained using data that has already been categorized to raise a red flag on to any transactions that seem suspicious.  In unsupervised learning, what happens is that raw, uncategorised data is introduced to the system, making it start from scratch. By interacting with that data, the system starts to identify patterns indicative of money laundering activities while also creating new ways to sort and analyse data.

The bottom line

As intelligent as this tech may be, it’s only as good as the data you feed it, so investing in talent should remain a top priority. You can’t expect any model employing AI to work without any sort of human input or testing – not yet, at least. Take transaction monitoring, for example. Each transaction needs to be evaluated against a set of risk-based rules. Even the most advanced monitoring systems to date leave banks with a substantial number of false positives, and that’s when the reviewer comes in to cast a human eye over the results before moving forward. In order for any financial institution to get the best out of its human and tech resources, the two need to work hand in hand. Employees need to feel empowered to work with machines and AI, and tech needs a human element in order to continue moving the industry forward.

ComplyRadar to the rescue

ComplyRadar monitors transactions relating to individuals, accounts, and entities to detect suspicious activity – quickly and effectively. Its machine learning transaction filter provides an additional probabilistic layer on top of the rules engine. This not only drastically reduces false positives but also provides additional data output which is not being captured by rules. For example, the machine learning algorithm can identify that a particular new combination of data is resulting in suspicious transactions. Contact us for more information on how ComplyRadar can automatically identify and react to suspicious behaviour in real-time or retrospectively while minimising unnecessary alerts.

Key challenges Financial Institutions face when tuning AML Transaction Monitoring software

Financial institutions across the globe are under unprecedented regulatory pressure to improve their AML Transaction Monitoring systems and ensure they are correctly tuned to detect money laundering and terrorist financing. Recent fines given to institutions who failed to detect suspicious activity and therefore meet regulatory standards have served to demonstrate the importance of having an effective compliance program and the right rule-tuning in place.

Finding the right balance in rule-tuning

Getting the tuning right can be challenging without the appropriate configuration. Solutions can either generate too many false positives, or the scenarios can be “turned down” so that genuine suspicious activity goes undetected. While triggering excessive false positive alerts costs both time and resources – as compliance teams struggle to handle the high number of alerts in depth – doing the opposite and performing tuning to reduce the amount of false positives can lead to officers overlooking suspicious activity, thus undermining the efficacy of the compliance program and potentially subjecting the company to regulatory scrutiny and eventual penalties.

The various AML Transaction Monitoring rules 

Rules can vary in complexity depending on the monitoring needs of the institution in question, and are designed to monitor customer activity outside the scope and ability of profile-based monitoring. Here are a few of the many rules that can provide the tools necessary to fine-tune an AML Transaction Monitoring solution, as well as the challenges they may pose.

In an attempt to reduce false positives, financial institutions often create exclusion lists. These are lists of customers they’ve marked as “non-suspicious” and therefore excluded from the transaction monitoring rules based on their historical alerts which were ultimately flagged as false positives. While this approach certainly does its job in reducing false positives, these lists must be reviewed regularly for potential changes in their transactional behaviour to prevent illegitimate transactions getting through undetected and unimpeded.

The objective of the structuring rule is to identify attempts to avoid regulatory reporting of a large cash transaction by breaking the transaction into smaller amounts that fall below the reporting threshold. However, a legitimate businessperson may make a number of deposits in amounts that look similar to a structuring pattern, in which case, the rules needs to be tuned to trigger an alert based on a combination of the pattern of the transactions and the profile of the customer, rather than the transaction activity alone.

The aim of applying a velocity rule is to identify suspicious activity and flag accounts where there is rapid movement of funds into and out of an account, such as a large part of a deposit which is debited from an account in a short period of time. However, if a customer instantly pays off a high volume of bills upon receiving their monthly pay, this could trigger an alert because of the velocity of the transactions. Therefore, such legitimate behaviour patterns need to be taken into account when tuning the software in order to reduce triggering false positives.

A final challenge of tuning rules is that it is not a one-time task. Rules need to be continuously applied and reviewed over time to identify potential new risks that are not covered by the current monitoring process in place. 

Ensure effective AML Transaction Monitoring with ComplyRadar

ComplyRadar minimises false positives by tailoring scenarios to customer or transaction risk. It enables you to increase effectiveness over time by fine tuning rules through back testing without the need of technical personnel. Contact us for more information on how we can help you give regulators and banking partners confidence with a clear audit trail of monitoring and investigations.

Why manual AML Transaction Monitoring processes do not scale in iGaming & Gambling companies

With the rise of money laundering and online fraud, iGaming & Gambling companies everywhere have had to up their game and optimise their transaction monitoring solutions against such risks. Leading iGaming & Gambling businesses across the globe have even been heavily fined by the relevant authorities for failures related to compliance. Therefore, a good AML transaction monitoring solution is important not only to prevent crime and protect your brand, but also to keep regulators happy and to grow your business. In this article, we measure the weaknesses of manual transaction monitoring against the strengths of its automatic counterpart. 

Recurring problems with manual AML transaction monitoring

Reduced Productivity

There are only so many cases and transactions that each member on the team can work on manually, which results in a significantly lower throughput. When cases are highly involved, a manual transaction monitoring process may not have the capacity to deal with them as quickly or as efficiently as required. 

Higher Costs

The number of cases and transactions will increase as your business grows, leading to a need for more employees to handle the growing number of cases and thus resulting in a greater overall expense.

Lack of consistency

Each compliance officer processes things in a different way due to differing working styles. The resulting inconsistency means that suspicious activity may only be detected by a certain number of officers. Because manual transaction monitoring relies on the capacity of human memory, officers often need to pause their work to take notes, having to stop whatever they are doing and start again. This situation is often aggravated when there are multiple cases to work on.

More room for error

Transaction monitoring processes have to evolve with the times as techniques for money laundering change. This means having to train and re-train old and new employees – and even with the best instructors, mistakes can frequently occur when processes change or when there are judgement calls to be made.

ComplyRadar monitors transactions relating to individuals, accounts, and entities to detect suspicious activity – quickly and effectively. It automates the AML transaction monitoring process, empowering you to automatically identify and react to suspicious behaviour in real-time or retrospectively while minimising unnecessary alerts.

ComplyRadar also enables you to:

  • Avoid reputational risk and potential fines
  • Improve customer experience and increase retention
  • Reduce human error and reliance on reports
  • Automate time-consuming manual compliance processes
  • Decrease the number of tools needed for the compliance team
  • Easily adapt to ongoing regulatory changes
  • Simplify auditing through an electronic audit trail of investigations

For more information on how ComplyRadar can help you maintain the right balance between stringent regulation and customer experience, contact us today.