juniorDimensionality Reduction
What is explained variance in PCA?
Updated May 16, 2026
Short answer
Explained variance measures how much information each principal component retains.
Deep explanation
It is the proportion of dataset variance captured by each principal component. Higher explained variance indicates better representation of original data.
Real-world example
Choosing components that retain 95% variance in image compression.
Common mistakes
- Assuming more components always improve performance.
Follow-up questions
- What is cumulative explained variance?
- How is it used in model selection?