Google Cloud Professional Machine Learning Engineer — Question 71

You are building a linear model with over 100 input features, all with values between –1 and 1. You suspect that many features are non-informative. You want to remove the non-informative features from your model while keeping the informative ones in their original form. Which technique should you use?

Answer options

• A. Use principal component analysis (PCA) to eliminate the least informative features.
• B. Use L1 regularization to reduce the coefficients of uninformative features to 0.
• C. After building your model, use Shapley values to determine which features are the most informative.
• D. Use an iterative dropout technique to identify which features do not degrade the model when removed.

Correct answer: B

Explanation

The correct answer is B because L1 regularization, also known as Lasso regression, effectively reduces the coefficients of non-informative features to zero, thereby excluding them from the model. Option A is incorrect as PCA transforms features rather than selectively removing them while retaining original informative ones. Option C does not prevent the inclusion of non-informative features in the model, and Option D focuses on feature removal but does not guarantee that informative features remain intact.