Why is it important to use the same evaluation metric when comparing different models?

To guarantee the models will have identical predictions

To reduce the size of the test dataset

To make the comparison consistent and meaningful

To ensure the models are trained with the same algorithm

In MLflow, what is the role of the Model Registry?

To create data pipelines for feature engineering

To automatically retrain models on a schedule

To log training metrics for each run

To store and manage versions of models, including staging and production stages

After selecting the best-performing model, a data scientist needs to save it so that it can be loaded later in a production REST API. The model is a scikit-learn pipeline that includes preprocessing steps and a classifier. What is the most appropriate way to store the model?

Save only the trained classifier's coefficients as a JSON file.

Export the model as a PMML file.

Serialize the entire pipeline using joblib or pickle.

Store the training script in a Git repository.

A data scientist trains a gradient boosting model and plots learning curves. The training error is very low and stays flat, while the validation error remains high and does not improve as more training data is added. What is the most appropriate next step?

Reduce model complexity, such as increasing regularization or reducing depth.

Increase model complexity, such as adding more trees or depth.

Switch to a simpler model like linear regression.

Add more training data to reduce the validation error.

CertNexusCertified Data Science Practitioner (CDSP)

Domain 4Objective 3

Objective 4.3 Evaluate Models CERTIFIED-DATA-SCIENCE-PRACTITIONER Practice Questions (Page 6)

Part of the 4.0 Building models domain, which accounts for 19-27% of the CERTIFIED-DATA-SCIENCE-PRACTITIONER exam.

30questions here

6free pages

8concepts

19-27%of the exam

Questions 26–30

26foundation · easy
Why is it important to use the same evaluation metric when comparing different models?
Select an answer first
27foundation · easy
In MLflow, what is the role of the Model Registry?
Select an answer first
28application · medium
After selecting the best-performing model, a data scientist needs to save it so that it can be loaded later in a production REST API. The model is a scikit-learn pipeline that includes preprocessing steps and a classifier. What is the most appropriate way to store the model?
Select an answer first
29application · medium
A data scientist trains a gradient boosting model and plots learning curves. The training error is very low and stays flat, while the validation error remains high and does not improve as more training data is added. What is the most appropriate next step?
Select an answer first
30application · medium
A data scientist is evaluating a model for predicting house prices. The business wants to know how far off predictions are on average in dollar terms. Which evaluation metric should be reported?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

No more pagesBack 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.