Skip to content

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

A risk analyst at an asset manager builds a supervised machine learning model to predict next-month default of corporate bonds. The model achieves near-perfect accuracy on the training data but performs poorly on a hold-out sample from a later period. Which diagnosis is most consistent with this pattern?

The pattern indicates overfitting. The model has memorized noise in the training data, so it scores almost perfectly in-sample but fails to generalize to a later hold-out sample. Underfitting would produce weak results in both samples, and leakage would flatter hold-out performance.

  1. AOverfitting, because the model has fitted noise specific to the training data and does not generalizeCorrect
  2. BUnderfitting, because the model is too simple to capture patterns in the training data
  3. CData leakage from the hold-out sample into the training set, which would inflate hold-out performance
  4. DMulticollinearity among inputs, which would reduce training accuracy

Explanation

Very high in-sample accuracy combined with weak out-of-sample performance is the classic sign of overfitting. Underfitting would show poor performance in both samples. Leakage from the hold-out into training would make hold-out results look better, not worse.

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