Home / ML Associate practice test / Model Development / Question

Databricks Machine Learning Associate · free practice question

A hospital readmission model will trigger costly interventions. The team wants the predicted probability itself to be trustworthy because downstream decisions…

Exam-style question on Model Development from the free ML Associate practice test, with the answer and a full explanation below.

Updated November 10, 2026

Model Development

A hospital readmission model will trigger costly interventions. The team wants the predicted probability itself to be trustworthy because downstream decisions depend on the confidence score, not just the positive or negative label. Which metric should be emphasized?

  1. AF1 score, because it optimizes the harmonic mean of precision and recall after choosing one operating threshold
  2. BLog loss, because it evaluates the full predicted probability distribution and penalizes poor confidence estimates
  3. CROC AUC, because it ignores calibration and therefore measures probability quality more directly than log loss
  4. DBalanced accuracy, because average recall by class is the standard measure of probability calibration for interventions
  5. EMean absolute percentage error, because intervention cost depends on relative percentage error in the probability values
Answer & explanation

Correct answer: B

WHY B: When calibrated probability quality matters, log loss is a strong choice because it scores the predicted probabilities directly. WHY NOT A: F1 depends on a threshold and ignores most probability information. WHY NOT C: ROC AUC measures ranking, not calibration quality. WHY NOT D: Balanced accuracy does not evaluate probabilities. WHY NOT E: MAPE is a regression metric and not standard for probability classification.

Take the full ML Associate practice test free →

Would you pass today?

This question is one of 45 in the free, timed Databricks Machine Learning Associate practice test. Take it and get a section-by-section score.

Start the free test →