Skip to content

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

Which feature of a random forest distinguishes it from plain bagging of decision trees?

A random forest considers only a random subset of predictors at each split, which decorrelates the trees and lowers the variance of the averaged prediction. Bootstrap sampling is shared with plain bagging, and sequential residual fitting describes boosting rather than random forests.

  1. AEach tree is trained on a bootstrap sample of the observations
  2. BAt each split only a random subset of predictors is considered, which decorrelates the treesCorrect
  3. CTrees are grown sequentially, each fitting the residuals of the previous one
  4. DPredictions are combined by weighting trees according to training error

Explanation

Both bagging and random forests use bootstrap samples. A random forest additionally restricts each split to a random subset of predictors, reducing correlation among trees and so the variance of the averaged prediction. Sequential residual fitting describes boosting.

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