Regulators expect compliance with the standards established in the model risk management guidance (MRMG) (Federal Reserve SR Letter 11-7, OCC Bulletin 2011-12; FDIC FIL 22-2017) as well as the April 9, 2021, Interagency Statement on Model Risk Management for Bank Systems Supporting Bank Secrecy Act/Anti-Money Laundering Compliance. This guidance relates to systems or models used by banks to assist in complying with the requirements of Bank Secrecy Act laws and regulations.
The following five components illustrate the importance of ongoing tuning as a critical component of the AML compliance program:
- Optimal Performance: Model tuning helps modify parameters to achieve the best performance, ensuring your model is calibrated to the specific characteristics of your data and to the risk profile of your institution.
- Filtering criteria/Thresholds: Tuning prevents over filtering or under filtering by finding the right balance. You want to ensure that the filtering and threshold configurations are set up correctly so that suspicious activity is not missed. This typically occurs when thresholds are set too high. Conversely setting thresholds too low can result in too many false positives which can lead to increased operational costs and create inefficiencies in the investigation process. You should pay particular attention to suspicious activity monitoring scenarios, rules or agents which produce few to no SARs or those which generate very few or no alerts.
- Resource Efficiency: The benefits of tuning can potentially reduce workload, allowing more time to be spent on meaningful alerts and improving the overall Anti-Money Laundering/Countering the Financing (AML/CFT) Program performance.
- Adaptability: Stay ahead of evolving threats. Another important aspect of model tuning lies in its ability to enhance the accuracy and efficiency of risk detection. As financial criminals become more sophisticated, their techniques evolve. Without regular tuning, detection models may become outdated and less effective in identifying emerging risks.
- Regulatory Compliance: Model tuning ensures that financial institutions remain compliant with the latest regulations, thereby avoiding potential legal consequences and reputational damage. Institutions that do not periodically evaluate their parameters could be subject to costly lookbacks, matters requiring attention, civil money penalties, memorandums of understanding, or cease and desist orders.
When did you last have your AMS independently validated? Although this is risk-based according to regulators, this should be outlined as part of model management. TCA specializes in model validation of multiple systems. Contact [email protected] if you would like us to discuss a potential engagement.
TCA – A Better Way!
