EasyDeepLearn

How do you decide how many PCA components to keep?

easy

Answer

  • Look at the cumulative explained-variance ratio and keep enough components to reach a target (e.g., 90% or 95%).
  • You can also inspect the scree plot for an elbow, or pick components based on downstream cross-validation performance.
  • Standardize features before PCA when they are on different scales.
Check yourself — multiple choice
  • Always keep just one component
  • Keep components until cumulative explained variance hits a target
  • PCA does not need standardization
  • Number of components must equal number of features

Cumulative explained variance is the standard criterion.

#dimensionality-reduction

Practise Unsupervised Learning

214 interview questions in this topic.

Related questions