AML Transaction Monitoring

Next-gen money laundering detection requires new approaches to monitoring financial transactions.

modern architecture
Radial circle

5 tenets for successful AML transaction monitoring

 

1. Banks are challenged with siloed data and disparate, disconnected systems. They need the ability to integrate flexibly with the system landscape, monitor each transaction, customer, and any other data points to build a holistic view of the customer and the associated level of risk.

2. Content of Suspicious Activity Reports (SARs) must be fact based. Even if the decision to raise a SAR is suspicion based, this evidence comes from the transactions and transaction history.

3. Transaction monitoring is a huge undertaking that requires automation and the application of AI and machine learning. Technology that prioritizes cases allows reporting officers to focus on where suspicion is likely to be the strongest.

4. A risk-based approach requires financial organizations to carefully assess all potential risks — understanding account transactions is intrinsic to this.

5. Transaction monitoring looks at risk associated with the transaction itself and screens against sanctions watchlists.

What is AML transaction monitoring?

 

AML transaction monitoring is also, and perhaps more aptly, called suspicious activity monitoring. It sees each payment transaction, regardless of payment type, vetted for behavior that is not in line with the information provided by the customer during onboarding or is atypical for others in their peer group. In addition to transactions, it also monitors non-monetary events, often in conjunction with transactional behavior. The exact nature of transaction monitoring is subject to the business of a financial services company and their own risk landscape. For example, asset managers or insurance companies will focus more heavily on non-transactional activities due to the nature of their products. If suspicious activity is likely, then the institution will investigate and decide whether to report that activity to the appropriate authority, specifically a financial intelligence unit (FIU).

Payment transactions are compared to sanctions or embargo watchlists and certain blocking rules before the money leaves or enters the financial institution. Specific scrutiny is applied to payment networks involving partner banks. This correspondent banking often involves a chain of multiple other sending and receiving banks that are allowed to conduct cross-border transactions. Monitoring this activity ensures that money is not sent to a country, business, charity, non-government organization, or person that you should not do business with. This is typically called transaction filtering or screening.

Due to the heavily regulated nature and mandatory audit requirements, AML transaction monitoring is based on best practice rules, typologies, and extensive knowledge of financial crime. Next gen AML transaction monitoring solutions enhance this approach. Using machine learning and AI, including network analytics, enhances human-based expert knowledge to detect new modes of criminal activity faster and understand customer behavior and their relationships. This should be bolstered by an effective and automated alert and case management solution that prioritizes cases so that the resources of reporting officers are appropriately used and they are given the resources they need to access all relevant information and progress cases efficiently.

Building a successful AML transaction monitoring strategy

 

Why does AML transaction monitoring matter?

Approximately 370 billion financial transactions are carried out each year globally. This presents a significant challenge for financial institutions. How do they correctly analyze this volume of transactions on a consistent basis and detect money laundering activities, without over reporting cases to a degree that handicaps effective law enforcement.

Money laundering as a whole is a significant threat for many organizations. It’s estimated that between $800 billion and $2 trillion is lost to money laundering globally each year. This amounts to between 2% and 5% of global GDP. 

The true amount is likely to be significantly more as this estimate is only the money that can be accurately traced. 

Money laundering is not a trifling matter or something to be glossed over as an abstract topic. Criminals gain this money through financial crimes such as credit fraud, corruption, or cybercrime such as ransomware attacks affecting companies’ supply chains, as well as crimes against humanity and nature, for example human trafficking, illegal arms sales, or trade in endangered flora and fauna. In many cases, money laundering is done to finance terrorist attacks, which is why AML and CTF (counter-terrorist financing) are often used as complementary terms. Money laundering should matter to everyone, everywhere. It’s a basic tenet for the wellbeing of human societies.

 

The compliance conundrum

Traditional approaches to AML are prohibited by a basic conflict of objectives between data protection and using data for good, between the will to do the right thing and the massive cost pressure that banks are facing. Nowadays, compliance expenditure makes up the bulk of a bank’s cost, but does not provide an immediate business benefit by improving services for their customers.

We need to rethink the current approaches. The time has come to embrace new technologies for transaction monitoring, specifically artificial intelligence (AI) and machine learning.

Frequently, an increase in detection rates can only be achieved by accepting higher false positive rates.
 
Filing SARs based on too little evidence leads to accusations of defensive filing by the FIU and will increase the burden on law enforcement to a level where they simply can’t take effective action. Make the level of proof too high and money laundering will slip through, increasing the risk for financial institutions of:

  • Substantial punitive fines — These fines can sometimes amount to hundreds of millions or even billions of dollars.
  • Criminal proceedings — Which can permanently damage the brand of a financial institution.
  • Freezing of assets — Crippling the ability of that institution to be able to operate effectively.
  • Reputational damage — This can be irreversible in some cases, leading to job losses and pay cuts, which in turn leads to:
    • Loss of customers — This will cause a potentially catastrophic loss of revenue. 
    • Inability to attract new customers — Not being able to attract new customers can take away the ability to repair the damage of losing existing customers.
  • Economic sanctions — These sanctions impede an organizations’ ability to operate effectively.
  • Personal repercussions – Those responsible for anti-money laundering can be personally penalized by the regulators.

Regulators are often under intense pressure from other stakeholders to stop and prevent money laundering activities. This pressure leads to the implementation of a high volume of regulations at a speed that is difficult for financial institutions to adapt to while they are already struggling to keep up with existing issues, often with unsuitable technology and workflows. It can be compared to trying to achieve a goal that, over time, moves exponentially further and further away. 

More effective transaction monitoring solves the problem for the regulator, the FIUs, and the financial institutions. 

 

Artificial intelligence and AML transaction monitoring

Over the previous 25 years, increased digitization, a plethora of payment methods, and increased transaction volumes have made detecting and preventing money laundering exponentially more difficult. 

Today’s AI-based methods have already proven highly effective at operating in this environment, particularly when it comes to fraud detection. Their effectiveness far outstrips previous rule-based methods, and the use of this technology for fraud detection can be adapted and expanded to effectively monitor and manage the adjacent discipline of financial crime compliance.

Artificial intelligence has distinct advantages over systems that are exclusively rules-based, including:

 

Detection of patterns you’re NOT looking for

Rules-based detection scenarios only produce alerts based on already known and existing scenarios. Financial criminals are resourceful and adapt their methodologies. With no ability to detect new scenarios, rules-based systems will always be on the back foot and susceptible to “zero day” attacks. 
In the fast-changing world of financial crime, this isn’t good enough. AI provides detection of (so far) unknown behavioral patterns, leading to identification of more complex money laundering patterns. Improving effectiveness lowers the risk of fines and helps banks remain competitive for legitimate customers’ business. Also, AI allows us to use unstructured data in addition to the well-structured customer and account transaction data. Unstructured data might be the text of a letter of credit or an email. This can also reveal patterns we’re not seeing today, as well as use the data mined from these sources together with the structured data to apply network analytics. These graphical charts can either be used for exploratory detective work, or in turn, feed into the ongoing monitoring to create alerts based on suspected network activity. 

 

Reduction of false positives

This will lower compliance costs and improve the quality of the alerts, while speeding up the handling of alerts and allowing compliance officers and investigators to focus on the most relevant, high risk cases. The remaining rules will be easier and maintained with lower effort. Data collection and analysis can be automated to a higher degree by the combination of AI with traditional detection scenarios. Cost pressure will accelerate the adoption of AI in the compliance sector. Compliance departments should develop strategies on how to leverage these new technologies to contribute to their success.

 

How FICO helps

FICO provides comprehensive anti-money laundering solutions that work across the customer lifecycle. Our comprehensive approach to transaction monitoring works for a wide range of financial institutions, including retail and commercial banks as well as supporting correspondent banking and trade finances. Our AML solutions can be deployed across in-person and digital channels. We provide modular functionality that includes:

AML analytics

Know your customer

Transaction monitoring

Sanctions screening

Alert and case management

Contact Us

Connect with FICO for answers to all your product and solution questions. We look forward to hearing from you.