The global AML (anti-money laundering) software industry is growing each year with an expected growth of up to USD 1.7 billion by 2023. These softwares are introducing newer ways to counter money laundering, such as AML tuning and optimization.
The enhancement of countermeasures is directly proportional to the rise in money laundering cases and the introduction of newer ways to do so. For example, Florence ranked the highest in money laundering in 2018 with as many as 22 cases per 100,000 residents.
Anti-money laundering regulations have gotten more and more strict, thus leading to the formation of associations such as ACAMS (Association of Certified Anti-Money Laundering Specialists) and CFT (Countering Financing of Terrorism).
As with all rules and regulations, it is important to keep updating and tuning implementation from time to time. New ways of money laundering have also led to new and improved AML tuning methodology and Robotic Process Automation for identifying irregularities.
AML Tuning For Banks & Companies
AML rules exist to reduce the risk of money laundering, helping banks and companies’ finance departments identify and report any suspicious financial activity. Rules such as the 3310 AML compliance program dictate that every financial institution shall implement a written anti-money laundering program (AML model) that complies with the Bank Secrecy Act (30 U.S.C. 5311, et seq.).
However, simply implementing a compliance program doesn’t offer sufficient guarantee that it can eliminate the risk of money laundering. That is why there is a need for AML tuning.
AML Tuning – What is it?
Even the most effective AML models can get outdated or inefficient without regular tuning. Tuning here refers to adjusting parameters in such a way as to impact the number of generated alerts. The changes may include changing single or multiple parameters.
The idea is to set parameters in a way that money laundering alerts are generated correctly and reduce the need for an inquiry, all while increasing the potential accuracy
Adjusting Single Parameters
When setting a single parameter, say the deposit amount. Setting the amount too low might lead to too many alerts, and too high can lead to a loophole in your system.
For example, keeping it at a deposit of $1 million per month might show more than 100 results, while increasing it to $5 million might lead to missed alerts.
Adjusting Multiple Parameters
Another AML tuning methodology includes changing several parameters, adapting it according to your preference.
Using two or more parameters, say deposit, withdrawal, the regularity of deposits, and transaction count, will help you filter out more.
Using filters can help AML regulators determine a pattern and investigate potential money laundering cases.
For example, a one-time $1 million deposit might mean inheritance or winnings, while regular large deposits might indicate a pattern.
Why Tune AML Rules Regularly?
AML tuning techniques must be used regularly to ensure that regulators can tackle changes in trends, adaption by launderers, and maintaining AML detection with the best market practices.
Many AML Tuning methodologies can be used;
- Risk-based approach
- Population group approach
- Suppression logic
- Quantitative AML rule tuning
- Qualitative AML rule tuning
- Gap analysis
- Statistical tuning
The demand for AML regulators and AML tuning has been increasing hand-in-hand with the risk of money laundering. If you are seeking a solution around AML tuning or as an AML Regulator, APN Consulting can help. Get in touch with us today!