Databricks Certified Machine Learning Associate Preparation Details
The Databricks Certified Machine Learning Associate exam validates your ability to use Databricks for core machine learning tasks with AutoML, Unity Catalog, and MLflow. This guide maps every domain in the exam guide to verified Databricks documentation, covering data preparation, model development, and deployment. You can also explore more Databricks certification study guides on the Data Engineering category to keep building your skills.
Databricks Certified Machine Learning Associate Materials
| Coursera | Databricks Machine Learning Fundamentals |
| Udemy | Databricks Certified Machine Learning Associate |
| Whizlabs | Databricks Certified Machine Learning Associate |
Section 1: Databricks Machine Learning (38% of scored content)
Databricks Machine Learning
Identify the best practices of an MLOps strategy
MLOps Stacks: model development process as code
Best practices for operational excellence
Identify the advantages of using ML runtimes
Databricks Runtime for Machine Learning
Machine learning on Databricks
Databricks Runtime 18.0 for Machine Learning
Identify how AutoML facilitates model/feature selection.
Train regression models with AutoML Python API
Identify the advantages AutoML brings to the model development process
Introducing Databricks AutoML: A Glass Box Approach
Identify the benefits of creating feature store tables at the account level in Unity Catalog in Databricks vs at the workspace level
Feature tables in Unity Catalog
Work with feature tables in Workspace Feature Store (legacy)
Explore features in Unity Catalog
Create a feature store table in Unity Catalog
Feature tables in Unity Catalog
Feature Engineering Python API
Write data to a feature store table
Feature tables in Unity Catalog
Feature Engineering Python API
Train a model with features from a feature store table.
Feature Engineering Python API
Score a model using features from a feature store table.
Use features in online workflows
Describe the differences between online and offline feature tables
Databricks Online Feature Stores
Use features in online workflows
Identify the best run using the MLflow Client API.
Track model development using MLflow
Manually log metrics, artifacts, and models in an MLflow Run.
Track model development using MLflow
Log, load, and register MLflow models
Identify information available in the MLFlow UI
Track model development using MLflow
Register a model using the MLflow Client API in the Unity Catalog registry
Manage model lifecycle in Unity Catalog
Identify benefits of registering models in the Unity Catalog registry over the workspace registry
Migrate workflows and models to Unity Catalog
Manage model lifecycle in Unity Catalog
Identify scenarios where promoting code is preferred over promoting models and vice versa
Set or remove a tag for a model
Manage model lifecycle in Unity Catalog
Promote a challenger model to a champion model using aliases
Manage model lifecycle in Unity Catalog
Section 2: Data Processing (19% of scored content)
Data Processing
Compute summary statistics on a Spark DataFrame using .summary() or dbutils data summaries
Databricks Utilities (dbutils) reference
Remove outliers from a Spark DataFrame based on standard deviation or IQR
Create visualizations for categorical or continuous features
Notebook and SQL editor visualization types
Visualizations in Databricks notebooks and SQL editor
Compare two categorical or two continuous features using the appropriate method
crosstab (DataFrameStatFunctions)
Compare 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 appropriate
Section 3: Model Development (31% of scored content)
Model Development
Use 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 pipeline
Use Hyperopt’s fmin operation to tune a model’s hyperparameters
Perform random or grid search or Bayesian search as a method for tuning hyperparameters.
Hyperparameter tuning with Optuna
Parallelize single node models for hyperparameter tuning
Compare model types with Hyperopt and MLflow
Describe 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 process.
Use common classification metrics: F1, Log Loss, ROC/AUC, etc
MulticlassClassificationEvaluator
Use common regression metrics: RMSE, MAE, R-squared, etc.
Choose the most appropriate metric for a given scenario objective
MulticlassClassificationEvaluator
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 performance
Validation curves: plotting scores to evaluate models
Single estimator versus bagging: bias-variance decomposition
Section 4: Model Deployment (12% of scored content)
Model Deployment
Identify the differences and advantages of model serving approaches: batch, realtime, and streaming
Deploy models using Model Serving
Deploy models for batch inference and prediction
Deploy a custom model to a model endpoint
Tutorial: Deploy and query a custom model
Create custom model serving endpoints
Use pandas to perform batch inference
Perform batch inference using a Spark DataFrame
Deploy models for batch inference and prediction
Identify how streaming inference is performed with Delta Live Tables
Deploy models for batch inference and prediction
Deploy and query a model for realtime inference
Tutorial: Deploy and query a custom model
Query serving endpoints for custom models
Split data between endpoints for realtime interference
Serve multiple models to a model serving endpoint
Wrapping Up Databricks Certified Machine Learning Associate
This guide covered every domain of the Databricks Certified Machine Learning Associate exam, from feature engineering and MLflow tracking to model tuning and deployment. Working through each official documentation link will help you build hands on familiarity with the tools Databricks expects you to know. You can also explore more Databricks certification study guides on the Data Engineering category to keep building your skills. Have a question or tip? Leave a comment below.
Receive Updates on Databricks Certified Machine Learning Associate Exam
Want to be notified as soon as I post? Subscribe to the RSS feed / leave your email address in the subscribe section. Share the article to your social networks with the below links so it can benefit others.
