What is Ridge Regression?
Updated May 16, 2026
Short answer
Ridge regression adds L2 regularization to reduce overfitting.
Deep explanation
It penalizes large coefficients by adding λ∑β² to the loss function. This shrinks coefficients but does not set them to zero, improving generalization and reducing multicollinearity impact.
Real-world example
Used in pricing models where many correlated features exist.
Common mistakes
- Assuming ridge performs feature selection.
Follow-up questions
- How does alpha affect model complexity?
- When is ridge preferred over lasso?