Free Practice Questions for Databricks Certified Machine Learning Associate - December 9 onwards Certification
- Exam guide version:
- November 10, 2026
- Guide checked for updates:
- 21 Nov 2026
- Question bank created:
- 21 Nov 2026
- Question bank last updated:
- 21 Nov 2026
Study with 347 exam-style practice questions designed to help you prepare for the Databricks Certified Machine Learning Associate - December 9 onwards. All questions are aligned with the latest exam guide and include detailed explanations to help you master the material.
Your progress
Start Practicing
Start a quiz
Practice with randomly mixed questions from all topics
Exam experiences
Pass and fail outcomes from candidates who prepared here — advice, scores, and prep time.
Your saved questions
Open the list of questions you bookmarked during practice for this exam.
Study notes
Private notes per question, grouped by exam domain — opens on its own page, not inline on this overview.
Quiz History
Exam Details
Key information about Databricks Certified Machine Learning Associate - December 9 onwards
- Multiple choice
Retake the current live exam every two years
English (other languages to follow)
None allowed
Multiple-choice and multiple-selection
None required; related training highly recommended
Online proctored or test center
USD 200, plus applicable taxes
90
45 scored multiple-choice and multiple-selection questions, plus up to 10 unscored items
2 years
December 9, 2026
6 months of hands-on Databricks experience
Exam Topics & Skills Assessed
Skills measured (from the official study guide)
1: Databricks Machine Learning
1.1: Identify the best practices of an MLOps strategy
Identify the best practices of an MLOps strategy
1.2: Identify the advantages of using ML runtimes
Identify the advantages of using ML runtimes
1.3: Identify the benefits of creating feature store tables at the account level in Unity Catalog in Databricks vs at the workspace level
Identify the benefits of creating feature store tables at the account level in Unity Catalog in Databricks vs at the workspace level
1.4: Create a feature store table in Unity Catalog
Create a feature store table in Unity Catalog
1.5: Write data to a feature store table
Write data to a feature store table
1.6: Train a model with features from a feature store table
Train a model with features from a feature store table
1.7: Score a model using features from a feature store table
Score a model using features from a feature store table
1.8: Describe the differences between online and offline feature tables
Describe the differences between online and offline feature tables
1.9: Identify the best run using the MLflow Client API
Identify the best run using the MLflow Client API
1.10: Manually log metrics, artifacts, and models in an MLflow Run
Manually log metrics, artifacts, and models in an MLflow Run
1.11: Identify information available in the MLflow UI
Identify information available in the MLflow UI
1.12: Register a model using the MLflow Client API in the Unity Catalog registry
Register a model using the MLflow Client API in the Unity Catalog registry
1.13: Identify benefits of registering models in the Unity Catalog registry over the workspace registry
Identify benefits of registering models in the Unity Catalog registry over the workspace registry
1.14: Identify scenarios where promoting code is preferred over promoting models and vice versa
Identify scenarios where promoting code is preferred over promoting models and vice versa
1.15: Set or remove a tag for a model
Set or remove a tag for a model
1.16: Promote a challenger model to a champion model using aliases
Promote a challenger model to a champion model using aliases
1.17: Compare the performance of two MLflow runs to select a model for production
Compare the performance of two MLflow runs to select a model for production
1.18: Use Autologging to simplify the capture of performance metrics and hyperparameters
Use Autologging to simplify the capture of performance metrics and hyperparameters
2: Data Processing
2.1: Compute summary statistics on a Spark DataFrame using .summary() or dbutils data summaries
Compute summary statistics on a Spark DataFrame using .summary() or dbutils data summaries
2.2: Remove outliers from a Spark DataFrame based on standard deviation or IQR
Remove outliers from a Spark DataFrame based on standard deviation or IQR
2.3: Create visualizations for categorical or continuous features
Create visualizations for categorical or continuous features
2.4: Compare two categorical or two continuous features using the appropriate method
Compare two categorical or two continuous features using the appropriate method
2.5: Compare and contrast imputing missing values with the mean or median or mode value
Compare and contrast imputing missing values with the mean or median or mode value
2.6: Impute missing values with the mode, mean, or median value
Impute missing values with the mode, mean, or median value
2.7: Use one-hot encoding for categorical features
Use one-hot encoding for categorical features
2.8: Identify and explain the model types or data sets for which one-hot encoding is or is not appropriate
Identify and explain the model types or data sets for which one-hot encoding is or is not appropriate
2.9: Identify scenarios where log scale transformation is appropriate
Identify scenarios where log scale transformation is appropriate
3: Model Development
3.1: Use ML foundations to select the appropriate algorithm for a given model scenario
Use ML foundations to select the appropriate algorithm for a given model scenario
3.2: Identify methods to mitigate data imbalance in training data
Identify methods to mitigate data imbalance in training data
3.3: Compare estimators and transformers
Compare estimators and transformers
3.4: Develop a training pipeline
Develop a training pipeline
3.5: Perform random or grid search or Bayesian search as a method for tuning hyperparameters
Perform random or grid search or Bayesian search as a method for tuning hyperparameters
3.6: Parallelize single node models for hyperparameter tuning
Parallelize single node models for hyperparameter tuning
3.7: Describe the benefits and downsides of using cross-validation over a train-validation split
Describe the benefits and downsides of using cross-validation over a train-validation split
3.8: Perform cross-validation as a part of model fitting
Perform cross-validation as a part of model fitting
3.9: Identify the number of models being trained in conjunction with a grid-search and cross-validation process
Identify the number of models being trained in conjunction with a grid-search and cross-validation process
3.10: Use common classification metrics: F1, Log Loss, ROC/AUC, etc
Use common classification metrics: F1, Log Loss, ROC/AUC, etc
3.11: Use common regression metrics: RMSE, MAE, R-squared, etc
Use common regression metrics: RMSE, MAE, R-squared, etc
3.12: Choose the most appropriate metric for a given scenario objective
Choose the most appropriate metric for a given scenario objective
3.13: Identify the need to exponentiate log-transformed variables before calculating evaluation metrics or interpreting predictions
Identify the need to exponentiate log-transformed variables before calculating evaluation metrics or interpreting predictions
3.14: Assess the impact of model complexity and the bias variance tradeoff on model performance
Assess the impact of model complexity and the bias variance tradeoff on model performance
3.15: Use Optuna to perform distributed hyperparameter tuning
Use Optuna to perform distributed hyperparameter tuning
3.16: Assess whether a machine learning approach is appropriate for a business problem based on data availability, baseline performance, and ROI considerations
Assess whether a machine learning approach is appropriate for a business problem based on data availability, baseline performance, and ROI considerations
3.17: Compare the computational requirements, training time, and data needs of deep learning versus traditional machine learning algorithms for a given problem
Compare the computational requirements, training time, and data needs of deep learning versus traditional machine learning algorithms for a given problem
3.18: Use SHAP values to explain individual model predictions and identify the most influential features for stakeholder communication
Use SHAP values to explain individual model predictions and identify the most influential features for stakeholder communication
3.19: Use feature importance scores to perform feature selection and reduce model complexity
Use feature importance scores to perform feature selection and reduce model complexity
4: Model Deployment and Monitoring
4.1: Identify the differences and advantages of model serving approaches: batch, realtime, and streaming
Identify the differences and advantages of model serving approaches: batch, realtime, and streaming
4.2: Deploy a custom model to a model endpoint
Deploy a custom model to a model endpoint
4.3: Use pandas to perform batch inference
Use pandas to perform batch inference
4.4: Identify how streaming inference is performed with Lakeflow pipelines
Identify how streaming inference is performed with Lakeflow pipelines
4.5: Deploy and query a model for realtime inference
Deploy and query a model for realtime inference
4.6: Split data between endpoints for realtime inference
Split data between endpoints for realtime inference
4.7: Detect various drift types using Databricks Data profiling
Detect various drift types using Databricks Data profiling
4.8: Create a custom metric to support a given ML modeling need
Create a custom metric to support a given ML modeling need
4.9: Choose a deploy code or deploy model approach based on model size, training cost, and organizational complexity
Choose a deploy code or deploy model approach based on model size, training cost, and organizational complexity
Techniques & products