medium · FRM Part 2 Current Issues
A bank discovers that its transaction monitoring system for Anti-Money Laundering (AML) has a 99% false positive rate. As part of a risk-based approach, the bank implements a Machine Learning triage model.
What is the bank's primary ongoing obligation to regulators regarding this new model?
- To outsource the model's operation to a third-party vendor, thereby eliminating accountability for its errors.
- To provide 'explainability' for why specific alerts were suppressed and perform regular 'backtesting' of suppressed alerts.
- To ensure the model uses only three input features so that regulators can more easily maintain its overall simplicity.
- To prove conclusively that the model has zero false negatives, meaning it catches 100 percent of all money-laundering activity.
Sign up free to see the explanation and track your rank →
More FRM Part 2 Current Issues practice
- According to the BCBS standard for cryptoassets, a bank's to… — What is this limit?
- What primary balance (as a % of GDP) is required to stabilize the debt-to-GDP ratio?
- SVB's management removed interest rate hedges in 2022. According to the Economic Value of
- In monitoring model stability, which metric is commonly used to quantify the shift in dist
- What does a SHAP value of zero for a specific feature in a credit scoring model imply?
- A bank provides a 'NAV facility' to a private equity fund. If the fund's underlying assets
- If the firm's EBITDA declines, when can the lender intervene?
- If the underlying loans are quarterly-marked and illiquid, what is the most significant ri