Skip to content

FRM Part I · FRM Exam Part I · Machine Learning and Prediction

In k-fold cross-validation with k = 5 applied to a sample of 500 observations, how many observations are used to train the model in each iteration, and how many times is each observation used for validation?

Each iteration trains on 400 observations and validates on the remaining 100. Because every observation belongs to exactly one fold, it is used for validation exactly once and for training in the other four iterations.

  1. A400 observations for training; each observation validated exactly onceCorrect
  2. B100 observations for training; each observation validated exactly once
  3. C400 observations for training; each observation validated 5 times
  4. D100 observations for training; each observation validated 4 times

Explanation

With 5 folds of 100 observations each, every iteration trains on the other 4 folds, which is 400 observations, and validates on the held-out fold of 100. Each observation sits in exactly one fold, so it is used for validation exactly once and for training in the other four iterations.

Did you get it right without looking?

One question tells you little. A timed set on Machine Learning and Prediction shows your real accuracy, how long you take and where you lose marks.

Practise Machine Learning and PredictionFree diagnostic mock

More Machine Learning and Prediction questions