Check your understanding of this module before moving on.
?
0/3
Checkpoint quiz 3 questions
A quick check on this module's key ideas before you move on
Question 01
What is the main limitation of built-in feature_importances_?
B is correct. This is the same multicollinearity-flavored problem from the regression lessons: correlated features can each look less important than the underlying signal actually is.
Question 02
How does permutation importance measure a feature's importance?
B is correct. Shuffling one feature while keeping everything else intact isolates exactly how much the model's real performance depends on that feature, without needing to retrain anything.
Question 03
What does partial dependence show that an importance score doesn't?
B is correct. Importance scores rank features. Partial dependence instead shows how the prediction changes as one feature varies, revealing the direction and shape of its effect.