A team has trained a custom churn-prediction model using scikit-learn. They need to deploy it to Databricks Model Serving with a custom preprocessing step that scales features before prediction. They have already registered the model in Unity Catalog. What is the required first step to make this custom logic available for serving?

Save the preprocessing script as a notebook and attach it to the model version in the Unity Catalog UI.

Register the preprocessing code as a separate model and reference it in the serving endpoint configuration.

Use mlflow.sklearn.log_model with the preprocessing pipeline as a parameter.

Create a Python class that inherits from mlflow.pyfunc.PythonModel and implement the predict method, then log it with mlflow.pyfunc.log_model along with any artifacts.

A team has a custom PyFunc model that requires a GPU for inference. They want to deploy it to Databricks Model Serving. What should they do?

Select a GPU-enabled serving endpoint type when creating the endpoint.

Use a CPU-only endpoint and rely on the model to run on CPU.

Convert the model to a format that does not require GPU.

Deploy the model on a cluster with GPU and use a reverse proxy.

A team has registered a custom PyFunc model in Unity Catalog. They want to deploy it to Model Serving using the UI. What information do they need to provide in the UI?

The model name and version to serve.

The path to the model's Python code.

The compute cluster to run the model.

A data scientist wants to deploy a registered custom model to a serving endpoint using the Databricks UI. Which sequence of steps correctly accomplishes this?

Navigate to Jobs → create a new job → select 'Model Serving' as the task type → configure → run

Navigate to Compute → select a cluster → click 'Deploy model' → choose the model → create endpoint

Navigate to Workspace → right-click the model file → select 'Deploy to endpoint' → configure → create

Navigate to MLflow → Models → select the model → click 'Serve this model' → configure the endpoint → create

A machine learning engineer has a registered custom PyFunc model in Unity Catalog and wants to deploy it to a Model Serving endpoint using the MLflow Deployments SDK. Which method on the client object creates the endpoint?

client.deploy(name="my_endpoint", model="catalog.schema.model", version=1)

client.start_endpoint(name="my_endpoint", model="catalog.schema.model", version=1)

client.serve(name="my_endpoint", model_uri="models:/catalog.schema.model/1")

client.create_endpoint(name="my_endpoint", config={"served_models": [{"model_name": "catalog.schema.model", "model_version": 1}]})

DatabricksCertified Machine Learning Professional

Domain 3Objective 2

Custom Model Serving MACHINE-LEARNING-PROFESSIONAL Practice Questions (Page 1)

Part of the Model Deployment domain, which accounts for 12% of the MACHINE-LEARNING-PROFESSIONAL exam. Databricks does not publish an official question count, but from its 120-minute exam (~50–80 total, ~6–10 in this domain), expect 3–5 from this objective — we provide 17 practice questions to prepare you well beyond it. (estimate)

17questions here

4free pages

3concepts

12%of the exam

Questions 1–5

1application · medium
A team has trained a custom churn-prediction model using scikit-learn. They need to deploy it to Databricks Model Serving with a custom preprocessing step that scales features before prediction. They have already registered the model in Unity Catalog. What is the required first step to make this custom logic available for serving?
Select an answer first
2expert · hard
A team has a custom PyFunc model that requires a GPU for inference. They want to deploy it to Databricks Model Serving. What should they do?
Select an answer first
3application · medium
A team has registered a custom PyFunc model in Unity Catalog. They want to deploy it to Model Serving using the UI. What information do they need to provide in the UI?
Select an answer first
4foundation · easy
A data scientist wants to deploy a registered custom model to a serving endpoint using the Databricks UI. Which sequence of steps correctly accomplishes this?
Select an answer first
5foundation · easy
A machine learning engineer has a registered custom PyFunc model in Unity Catalog and wants to deploy it to a Model Serving endpoint using the MLflow Deployments SDK. Which method on the client object creates the endpoint?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to MACHINE-LEARNING-PROFESSIONAL

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Databricks. “MACHINE-LEARNING-PROFESSIONAL” is a trademark of its owner, used for identification only.