2. Supervised Learning

Model Evaluation — Quiz

Test your understanding of model evaluation with 5 practice questions.

Practice Questions

Question 1

When evaluating a binary classification model, which of the following metrics is most suitable for scenarios where both false positives and false negatives are equally costly?

Question 2

In the context of cross-validation, what is the primary purpose of shuffling the data before splitting it into folds?

Question 3

Consider a scenario where a machine learning model is used to predict rare events, such as equipment failure. Which evaluation metric would be most appropriate to assess the model's ability to correctly identify these rare positive instances?

Question 4

What is the primary advantage of using a Precision-Recall (PR) curve over a Receiver Operating Characteristic (ROC) curve when evaluating a binary classification model on an imbalanced dataset?

Question 5

In the context of model calibration, what does a perfectly calibrated model imply about its predicted probabilities?