3.7 Dimension reduction

Dimension reduction is an alternative approach to filter out non-informative features without manually removing them. We discuss dimension reduction topics in depth later in the book (Chapters 17-19) so please refer to those chapters for details.

For example, we may wish to reduce the dimension of our features with principal components analysis (Chapter 17) and retain the number of components required to explain, say, 95% of the variance and use these components as features in downstream modeling.