A data science team is evaluating a model for a fraud detection system. The test set has 1% fraud cases. The model achieves 99% accuracy, but the recall for fraud is 0.20. Which evaluation approach would best reveal the model's true performance?

Examine the precision-recall curve for the fraud class

Use the F1-score for the majority class

A binary classifier has a test-set ROC AUC of 0.98, but the precision-recall AUC is 0.20. The positive class is very rare (0.5% of the data). Which conclusion is most appropriate?

The model is biased toward the majority class.

The model is overfitting because the ROC AUC is high.

The model ranks positives well but has low precision for the rare positive class.

CertNexusCertified Data Science Practitioner (CDSP)

Domain 5Objective 7

Evaluate Test Results CERTIFIED-DATA-SCIENCE-PRACTITIONER Practice Questions (Page 2)

Part of the 5.0 Testing models domain, which accounts for 4-7% of the CERTIFIED-DATA-SCIENCE-PRACTITIONER exam.

20questions here

4free pages

1concept

4-7%of the exam

Questions 6–10

6application · easy
A data scientist evaluates a binary classifier and obtains a confusion matrix with the following values: TP=50, FP=30, FN=10, TN=110. What is the recall of the model?
Select an answer first
7application · medium
A data science team is evaluating a model for a fraud detection system. The test set has 1% fraud cases. The model achieves 99% accuracy, but the recall for fraud is 0.20. Which evaluation approach would best reveal the model's true performance?
Select an answer first
8application · medium
A binary classifier has a test-set ROC AUC of 0.98, but the precision-recall AUC is 0.20. The positive class is very rare (0.5% of the data). Which conclusion is most appropriate?
Select an answer first
9application · medium
A regression model predicts delivery times. The test set has a few instances with extremely long delivery times due to rare logistical failures. Which metric would be most appropriate to evaluate the model's typical performance?
Select an answer first
10application · easy
A binary classifier is evaluated on a test set. The confusion matrix shows: true positives = 40, false positives = 10, false negatives = 20, true negatives = 130. What is the precision of the model?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to CERTIFIED-DATA-SCIENCE-PRACTITIONER

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by CertNexus. “CERTIFIED-DATA-SCIENCE-PRACTITIONER” is a trademark of its owner, used for identification only.

Evaluate Test Results CERTIFIED-DATA-SCIENCE-PRACTITIONER Practice Questions (Page 2)

Questions 6–10

A data scientist evaluates a binary classifier and obtains a confusion matrix with the following values: TP=50, FP=30, FN=10, TN=110. What is the recall of the model?

A data science team is evaluating a model for a fraud detection system. The test set has 1% fraud cases. The model achieves 99% accuracy, but the recall for fraud is 0.20. Which evaluation approach would best reveal the model's true performance?

A binary classifier has a test-set ROC AUC of 0.98, but the precision-recall AUC is 0.20. The positive class is very rare (0.5% of the data). Which conclusion is most appropriate?

A regression model predicts delivery times. The test set has a few instances with extremely long delivery times due to rare logistical failures. Which metric would be most appropriate to evaluate the model's typical performance?

A binary classifier is evaluated on a test set. The confusion matrix shows: true positives = 40, false positives = 10, false negatives = 20, true negatives = 130. What is the precision of the model?

Keep studying — 5.0 Testing models