Chapter 8 Feature Selection For Machine Learning

Question 1

WHAT ARE SOME TECHNIQUES FOR FEATURE ENGINEERING/SELECTION IN SCIKIT-LEARN? P61

Answer 1

Univariate Selection.
Recursive Feature Elimination.
Principle Component Analysis.
Feature Importance

Question 2

WHAT ARE 3 BENEFITS OF PERFORMING FEATURE SELECTION BEFORE MODELING? P61

Answer 2

ˆ Reduces Overfitting: Less redundant data means less opportunity to make decisions based on noise.
ˆ Improves Accuracy: Less misleading data means modeling accuracy improves.
ˆ Reduces Training Time: Less data means that algorithms train faster.