Data Science Feature Engineering and Selection 3

Question 1

Which feature selection method evaluates subsets of features using the actual model's performance?

Accepted Answer

Wrapper methods

Answer

Wrapper methods (e.g., recursive feature elimination) train the model to score feature subsets.

Question 2

Filter methods select features based on:

Accepted Answer

Statistical measures independent of any model

Answer

Filter methods rank features by statistics like correlation or chi-square, independent of a model.

Question 3

L1 (Lasso) regularization performs feature selection by:

Accepted Answer

Shrinking some coefficients exactly to zero

Answer

L1 penalty can drive coefficients to exactly zero, effectively removing those features.

Question 4

Two features have a correlation of 0.97. What is a common action in feature selection?

Accepted Answer

Drop one of the redundant features

Answer

Highly correlated features are redundant, so dropping one reduces multicollinearity.

Question 5

Which metric measures multicollinearity among features?

Accepted Answer

Variance Inflation Factor (VIF)

Answer

VIF quantifies how much a feature is linearly explained by the others.

Data Science Practice Test