Skip to content

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

A quantitative team at an asset manager trains a gradient-boosted model to predict next-month equity returns. In-sample R-squared is very high, but out-of-sample performance is close to zero. Which diagnosis is most consistent with this pattern?

The pattern points to overfitting. A flexible model fitted noise unique to the training data, so in-sample fit is high but out-of-sample performance collapses. Underfitting would show weak results in both samples, not a large gap between them.

  1. AUnderfitting, because the model is too simple to capture the signal
  2. BOverfitting, because the model has learned noise specific to the training sampleCorrect
  3. CSurvivorship in the loss function, because gradient boosting ignores errors
  4. DMulticollinearity, because the model has too few predictors

Explanation

A large gap between strong in-sample fit and poor out-of-sample results is the classic sign of overfitting: the flexible model has fitted noise rather than stable relationships. Underfitting would produce poor performance in both samples.

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