PMLE Monitoring ML Solutions Practice Question

A machine learning engineer wants to monitor the fairness of a credit approval model across demographic subgroups. They have ground truth labels in BigQuery. Which approach should they use to evaluate performance disparities?

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Use Vertex AI Model Evaluation with sliced evaluation in BigQuery

Vertex AI Model Evaluation supports sliced evaluation, allowing comparison of metrics (like accuracy, precision) across subgroups defined by features like age, gender, etc.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✓
Use Vertex AI Model Evaluation with sliced evaluation in BigQuery
Why this is correct
Correct: Sliced evaluation computes metrics per subgroup to identify disparities.
✗
Use Vertex AI Explainability to compute feature attributions per subgroup
Why it's wrong here
Explainability shows feature importance but does not directly evaluate performance disparities.
✗
Use Cloud Monitoring custom metrics to track predictions per subgroup
Why it's wrong here
Custom metrics can track counts but not performance metrics like accuracy or fairness.
✗
Use Vertex AI Model Monitoring to detect skew in demographic features
Why it's wrong here
Skew detection does not evaluate model performance across subgroups.

Go deeper

PMLE Monitoring ML Solutions Practice Question

Why each option matters

Option-by-option breakdown

Related to this question