Chapter 1 of 4 · Databricks Machine Learning Associate
Databricks Machine Learning
MLOps, ML runtimes, AutoML, Unity Catalog feature tables, MLflow tracking, registry and aliases.
- 6topics
- 30 minfast track
- 2diagrams and exhibits
- 38%of the exam
Topics in this chapter
Take them in order, or jump to the one you need.
- 1MLOps Strategy, ML Runtimes and PromotionDatabricks ML Associate: MLOps best practices, why Databricks Runtime for ML helps, and when to promote training code versus…5 min
- 2AutoML for Model and Feature SelectionDatabricks ML Associate: how AutoML prepares data, selects columns, tries several algorithms, ranks trials in MLflow and gives…5 min
- 3Feature Tables in Unity CatalogDatabricks ML Associate: why Unity Catalog feature tables beat workspace ones, plus create_table and write_table with…5 min
- 4Training and Scoring with Feature TablesDatabricks ML Associate: build a training set with FeatureLookup, log the model with fe.log_model, score with score_batch, and…Diagram5 min
- 5MLflow Runs, Manual Logging and the UIDatabricks ML Associate: log metrics, params, artifacts and models by hand in MLflow, find the best run with search_runs, and…5 min
- 6Unity Catalog Model Registry, Tags and AliasesDatabricks ML Associate: register models in Unity Catalog with the MLflow client, why UC beats the workspace registry, model…Diagram5 min
About this chapter
What this chapter covers
Databricks Machine Learning is 38% of the Databricks Machine Learning Associate exam, the largest chapter by far. It covers the platform tools you use around a model: the compute it runs on, the features it reads, the runs it logs and the registry it lives in.
The chapter has six parts: MLOps strategy and ML runtimes, AutoML, creating and writing feature tables in Unity Catalog, training and scoring with those features (online versus offline), tracking work with MLflow, and registering, tagging and promoting models in the Unity Catalog registry.
Questions are single-answer and multiple-selection ("Which TWO ...?"), mostly short scenarios. Some show a short Python snippet (MLflow, Feature Engineering client, Spark ML, Model Serving) and ask what it does or which call meets a requirement. There are no exhibits.
How the topics fit together
You start on an ML runtime cluster, where AutoML can give you a quick baseline. Features live in governed Unity Catalog tables, every training attempt is an MLflow run, and the chosen model is registered in Unity Catalog and promoted with aliases.
- MLOps questions ask how to organize environments, code and models, and when to promote code or models.
- Runtime and AutoML questions ask what comes preinstalled and what AutoML generates for you.
- Feature table questions ask which Feature Engineering client call creates, writes, trains or scores.
- MLflow questions ask how to log by hand, find the best run and read the UI.
- Registry questions ask how to register, tag and move the champion alias.
Watch for old names. The exam outline still says "feature store table" and "workspace registry"; the right answer almost always uses the Unity Catalog version (FeatureEngineeringClient, three-level names, aliases), not workspace stages or FeatureStoreClient.
How to use these pages
Each topic page has the same shape, so you can skim for what you need.
- What it is: the idea in plain words.
- How it works: the mechanism, with tables and examples.
- What to remember for the exam: the facts to memorize and how questions are phrased.
- Common mistakes: the classic traps.
- Check yourself: three questions to test your understanding.
Ready for more practice?
The full Databricks Machine Learning Associate question bank has 600 questions, with timed practice exams and an explanation for every answer.
This study guide is independent and is not affiliated with, endorsed by, or sponsored by Databricks. Vendor names, certification names and exam codes are trademarks of their respective owners and are used for identification only.