Home / ML Associate practice test / Databricks Machine Learning / Question

Databricks Machine Learning Associate · free practice question

A team used AutoML for a churn classification problem and now wants to understand the exact transformations and training code behind the strongest candidate…

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

Updated November 10, 2026

Databricks Machine Learning

A team used AutoML for a churn classification problem and now wants to understand the exact transformations and training code behind the strongest candidate. Which outcome should they expect from Databricks AutoML?

  1. AAutoML generates notebooks for the best trial and related experiment outputs so the team can review, reproduce, and modify the code behind the selected baseline instead of treating the process as a black box only
  2. BAutoML provides only a leaderboard score and a locked binary artifact, because Databricks intentionally hides feature processing and trial logic to prevent unsupported modifications to generated experiments
  3. CAutoML requires users to export every trial to an external Git repository before any generated training logic can be viewed, because experiment notebooks are never stored or referenced inside Databricks
  4. DAutoML exposes only SQL text for each trial, because Python trial notebooks are not compatible with MLflow experiment tracking and therefore cannot be attached to generated runs
  5. EAutoML returns a registered Unity Catalog model without any experiment history, because the intended workflow is to evaluate only the final artifact and skip inspection of trial-level training details
Answer & explanation

Correct answer: A

WHY A: Databricks AutoML generates source notebooks for trials, especially for the best trial and data exploration outputs, so users can inspect and adapt the baseline approach. WHY NOT B: AutoML is not limited to opaque binary outputs. WHY NOT C: Trial logic is available within Databricks workflows and artifacts. WHY NOT D: It does not expose only SQL. WHY NOT E: AutoML retains experiment history and trial artifacts rather than skipping them.

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 →