Databricks Certified Machine Learning Associate (Machine Learning Associate) practice exam and study path
A free, timed 48-question Machine Learning Associate practice exam in 90 minutes, scored by domain, with every option explained after you submit. Also 120 practice questions you can check one at a time, a page for every task in the exam guide, and a study path. No sign-up.
$6.99for 12 months
The foundational Databricks machine learning exam: MLOps practice and ML runtimes, AutoML, feature tables in Unity Catalog, MLflow tracking and the Unity Catalog model registry, exploring and preparing data in Spark, training, tuning and evaluating models with cross-validation and the right metrics, and deploying them for batch, streaming and real-time inference.
The exam
- Exam code
- Machine Learning Associate
- Questions
- Not yet published
- Time
- 90 minutes
- Passing score
- Not published
- Exam fee
- $200 (USD)
- Question types
- multiple choice, multiple response
48 scored multiple-choice and multiple-selection questions in 90 minutes (up to 10 unscored items may be added and are not identified), USD 200 plus applicable taxes, online proctored or at a test center, no test aids, in English, Japanese, Portuguese (BR) and Korean. No prerequisite; related training and six months of hands-on Databricks experience are recommended. Valid for 2 years; to recertify you take the current exam. Passing score: Not published. This outline is the version published March 1, 2025.
From Databricks's certification page and exam guide, checked Nov 11, 2026.
Domains and weights
Domain 1: Databricks Machine Learning
38%
Domain 2: Data Processing
19%
Domain 3: Model Development
31%
Domain 4: Model Deployment
12%
Practice
120 original practice questions, every option explained with the Databricks documentation page that proves it. Free, no sign-up; progress stays on this device.
120 questions · practice mode
All domains
Every sample question for this exam, in domain order.
48 questions · practice mode
Topic quiz — Domain 1: Databricks Machine Learning
A topic quiz on domain 1 (38% of the exam).
19 questions · practice mode
Topic quiz — Domain 2: Data Processing
A topic quiz on domain 2 (19% of the exam).
35 questions · practice mode
Topic quiz — Domain 3: Model Development
A topic quiz on domain 3 (31% of the exam).
18 questions · practice mode
Topic quiz — Domain 4: Model Deployment
A topic quiz on domain 4 (12% of the exam).
48 questions · 90 min · timed
Free practice exam
The real exam's pace, no feedback until you submit.
48 questions · 90 min · timed · exam pack
Practice exam 1
Included in the Machine Learning Associate exam pack.
48 questions · 90 min · timed · exam pack
Practice exam 2
Included in the Machine Learning Associate exam pack.
48 questions · 90 min · timed · exam pack
Practice exam 3
Included in the Machine Learning Associate exam pack.
More practice exams
The lessons, the sample questions on every task page and the first full practice exam are free and stay free. A pack adds the further timed Machine Learning Associate practice exams.
Machine Learning Associate exam pack
$6.99for 12 months
- Every paid Machine Learning Associate practice exam, timed, with every option explained
- The next version of this exam included when it changes within your 12 months
- 12 months of access. One payment, nothing renews by itself.
- 14-day refund, no conditions
- 14-day refund, no conditions: ask within 14 days of buying and you get the whole payment back.
- No pass guarantee. These are practice exams written by us from the exam guide and the Databricks documentation; a score here does not predict your result on the real exam.
Study path
One module per exam domain. Lessons that already exist on BytePatterns are linked; the rest are being written.
Module 1: Databricks Machine Learning
1MLOps on Databricks: environments as catalogs, deploy code, Git and MLflowTask 1.1
Partly covered by: From Pilot to Production
2Databricks Runtime for Machine Learning: preinstalled libraries and compute settingsTask 1.1
Lesson coming
3AutoML: data preparation, trials, generated notebooks and where it runsTask 1.2
Lesson coming
4Feature tables in Unity Catalog: create, write, train and scoreTask 1.3
Lesson coming
5Offline feature tables and online feature storesTask 1.3
Lesson coming
6MLflow tracking: runs, manual logging, search_runs and the MLflow UITask 1.4
Lesson coming
7Models in Unity Catalog: registering, tags, aliases and promotionTask 1.5
Lesson coming
Module 2: Data Processing
8Exploring data: summary statistics, data profiles and outliersTask 2.1
Partly covered by: Data Readiness for AI
9Visualizing and comparing features in notebooksTask 2.1
Lesson coming
10Imputing missing values: mean, median or modeTask 2.2
Lesson coming
11One-hot encoding and when not to use it; log transformsTask 2.2
Lesson coming
Module 3: Model Development
12Choosing an algorithm for a model scenarioTask 3.1
Partly covered by: What Is Machine Learning
13Imbalanced training data: class weights and resamplingTask 3.1
Lesson coming
14Spark ML estimators, transformers and training pipelinesTask 3.1
Lesson coming
15Hyperparameter tuning: grid, random and adaptive search, parallel trialsTask 3.2
Lesson coming
16Cross-validation versus a train-validation split; counting modelsTask 3.3
Partly covered by: What Is Machine Learning
17Classification and regression metrics and choosing oneTask 3.4
Lesson coming
18Log-scale targets and the bias-variance trade-offTask 3.4
Lesson coming
Module 4: Model Deployment
19Batch, streaming and real-time inferenceTask 4.1
Partly covered by: Training vs Inference
20Batch inference with pandas and Spark UDFs; models in Lakeflow pipelinesTask 4.1
Lesson coming
21Model Serving endpoints: deploy, query and split trafficTask 4.2
Lesson coming
Every task in the exam guide
The exam guide splits each domain into task statements. Each one has a page with a short summary, the lessons that teach it and open sample questions.
Domain 1: Databricks Machine Learning
- 1.1Identify the best practices of an MLOps strategy; Identify the advantages of using ML runtimes8 sample questions
- 1.2Identify how AutoML facilitates model/feature selection; Identify the advantages AutoML brings to the model development process8 sample questions
- 1.3Identify the benefits of creating feature store tables at the account level in Unity Catalog in Databricks vs at the workspace level; Create a feature store table in Unity Catalog; Write data to a feature store table; Train a model with features from a feature store table; Score a model using features from a feature store table; Describe the differences between online and offline feature tables12 sample questions
- 1.4Identify the best run using the MLflow Client API; Manually log metrics, artifacts, and models in an MLflow Run; Identify information available in the MLflow UI9 sample questions
- 1.5Register a model using the MLflow Client API in the Unity Catalog registry; Identify benefits of registering models in the Unity Catalog registry over the workspace registry; Identify scenarios where promoting code is preferred over promoting models and vice versa; Set or remove a tag for a model; Promote a challenger model to a champion model using aliases11 sample questions
Domain 2: Data Processing
- 2.1Compute summary statistics on a Spark DataFrame using .summary() or dbutils data summaries; Remove outliers from a Spark DataFrame based on standard deviation or IQR; Create visualizations for categorical or continuous features; Compare two categorical or two continuous features using the appropriate method8 sample questions
- 2.2Compare and contrast imputing missing values with the mean or median or mode value; Impute missing values with the mode, mean, or median value; Use one-hot encoding for categorical features; Identify and explain the model types or data sets for which one-hot encoding is or is not appropriate; Identify scenarios where log scale transformation is appropriate11 sample questions
Domain 3: Model Development
- 3.1Use ML foundations to select the appropriate algorithm for a given model scenario; Identify methods to mitigate data imbalance in training data; Compare estimators and transformers; Develop a training pipeline10 sample questions
- 3.2Use Hyperopt's fmin operation to tune a model's hyperparameters; Perform random or grid search or Bayesian search as a method for tuning hyperparameters; Parallelize single node models for hyperparameter tuning7 sample questions
- 3.3Describe the benefits and downsides of using cross-validation over a train-validation split; Perform cross-validation as a part of model fitting; Identify the number of models being trained in conjunction with a grid-search and cross-validation process9 sample questions
- 3.4Use common classification metrics: F1, Log Loss, ROC/AUC, etc; Use common regression metrics: RMSE, MAE, R-squared, etc; Choose the most appropriate metric for a given scenario objective; Identify the need to exponentiate log-transformed variables before calculating evaluation metrics or interpreting predictions; Assess the impact of model complexity and the bias variance tradeoff on model performance9 sample questions
Domain 4: Model Deployment
- 4.1Identify the differences and advantages of model serving approaches: batch, realtime, and streaming; Use pandas to perform batch inference; Identify how streaming inference is performed with Delta Live Tables9 sample questions
- 4.2Deploy a custom model to a model endpoint; Deploy and query a model for realtime inference; Split data between endpoints for realtime interference9 sample questions
How these questions are made
- Written by us from the exam guide's task statements and the Databricks documentation — never from real exam content.
- Every option carries its own explanation and a link to the Databricks page that proves it.
- A question enters a timed exam only after an independent check; until then it is a practice question.
- Results are a plain percentage, per domain too — not an imitation of Databricks's scaled score.
Questions about the Machine Learning Associate practice exam
- Is the Machine Learning Associate practice exam free?
- Yes. The full practice exam (48 questions, 90 minutes) is free with no sign-up, and so are the 120 practice questions, the task pages and the study path. Your attempts are saved in this browser, on this device.
- How many questions does it have, and is it timed?
- 48 questions in 90 minutes: the real Machine Learning Associate pace, scaled to this form. When the time runs out, the exam is submitted as it stands.
- Are the answers explained?
- After you submit, not during: like the real exam, the timed exam gives no feedback until the end. Then you get your score overall and per exam domain, and every question with each option explained and a link to the Databricks documentation page behind it. In practice mode an answer is explained as soon as you check it.
- What does the Machine Learning Associate exam pack add?
- 3 more timed practice exams (Practice exam 1: 48 questions, 90 minutes; Practice exam 2: 48 questions, 90 minutes; Practice exam 3: 48 questions, 90 minutes), each scored and explained the same way, and the next version of this exam if it changes within your 12 months. 12 months of access. One payment, nothing renews by itself. Everything above stays free. See the pack.
- Can I get a refund?
- Yes, with no conditions: ask within 14 days of buying and you get the whole payment back. The details are in the terms.
- Is this an official Databricks practice exam?
- No. BytePatterns is not affiliated with, endorsed or sponsored by Databricks. Every question is written by us from the public exam guide and the Databricks documentation, never from real exam content, and a score here does not predict your result on the real exam. Databricks lists its own preparation resources on its certification page.