The correct answer is: C. Both use subset selection of features.
Ridge regression and Lasso regression are both penalized regression methods that can be used for feature selection. In ridge regression, a penalty is added to the model’s loss function that penalizes the model for having too many features. This can help to prevent overfitting and can lead to more accurate models. Lasso regression is similar to ridge regression, but it also penalizes the model for having too many features. However, in lasso regression, the penalty is more severe, which can lead to some features being completely removed from the model.
Both ridge regression and lasso regression can be used for feature selection. However, they have different strengths and weaknesses. Ridge regression is more robust to overfitting, but it can be less accurate than lasso regression. Lasso regression is more accurate than ridge regression, but it can be more sensitive to overfitting.
The choice of which penalized regression method to use depends on the specific application. If overfitting is a concern, then ridge regression may be a better choice. If accuracy is a concern, then lasso regression may be a better choice.
Here is a brief explanation of each option:
- A. Ridge regression uses subset selection of features. This is true. Ridge regression is a penalized regression method that can be used for feature selection. In ridge regression, a penalty is added to the model’s loss function that penalizes the model for having too many features. This can help to prevent overfitting and can lead to more accurate models.
- B. Lasso regression uses subset selection of features. This is also true. Lasso regression is similar to ridge regression, but it also penalizes the model for having too many features. However, in lasso regression, the penalty is more severe, which can lead to some features being completely removed from the model.
- C. Both use subset selection of features. This is the correct answer. Both ridge regression and lasso regression can be used for feature selection.
- D. None of above. This is not true. Both ridge regression and lasso regression can be used for feature selection.