Skip to content

FRM Part II · FRM Exam Part II · Advances in Artificial Intelligence: Implications for Capital Markets Activities

A bank trains a machine learning credit-spread forecasting model on ten years of data covering a calm, low-volatility market regime. Shortly after deployment, a sharp regime shift occurs and forecast errors rise sharply. Which model risk issue best describes this?

This is model drift or poor out-of-sample generalization. The model learned relationships from a calm regime that did not represent stressed conditions, so when the regime shifted its forecasts degraded. Data leakage would instead inflate backtest results, not cause failure after deployment.

  1. AData leakage from using future information in training
  2. BModel drift or poor out-of-sample generalization because the training data did not represent the new regimeCorrect
  3. COverfitting caused by too few input variables
  4. DExcessive transparency of the model architecture

Explanation

Training on only a calm regime means the model has not seen stressed conditions, so relationships learned break down when the regime changes. This is a generalization or drift problem. Leakage would inflate backtests rather than cause post-deployment failure, and overfitting is typically linked to excess complexity, not too few variables.

Did you get it right without looking?

One question tells you little. A timed set on Advances in Artificial Intelligence: Implications for Capital Markets Activities shows your real accuracy, how long you take and where you lose marks.

Practise Advances in Artificial Intelligence: Implications for Capital Markets ActivitiesFree diagnostic mock

More Advances in Artificial Intelligence: Implications for Capital Markets Activities questions