A team has a model endpoint serving version 1 of a model. They have trained a new version (version 2) and want to update the endpoint to serve version 2 without downtime. What should they do?

Retrain the model and re-register it as version 1 to overwrite the existing version.

Create a second endpoint with version 2 and then redirect traffic using a load balancer.

Use the Databricks UI to edit the endpoint and change the model version from 1 to 2.

Delete the existing endpoint and create a new one with version 2.

A team has a model that requires an environment variable to be set at runtime (e.g., an API key for a downstream service). They want to deploy it to a model endpoint. What should they do?

Use the MLflow model's conda environment to set the environment variable.

Hardcode the API key in the model code and log the model.

Set the environment variable in the endpoint configuration using the UI or API.

Create a custom Docker image with the environment variable baked in.

Which action is part of managing the lifecycle of a model endpoint?

Deleting the endpoint when it is no longer needed

Retraining the model on the endpoint

Changing the model's training data

Modifying the model's algorithm

Which scenario best describes the use of a model endpoint?

A data pipeline that transforms raw data and trains a model

A dashboard that displays historical model performance metrics

A web application that sends a request and receives a prediction for each user action

A nightly job that scores a large dataset and writes results to a table

DatabricksCertified Machine Learning Associate

Domain 4Objective 2

Deploy a Custom Model to a Model Endpoint MACHINE-LEARNING-ASSOCIATE Practice Questions (Page 1)

Part of the Section 4: Model Deployment domain, which makes up ~30% of our current practice bank. Databricks does not publish an official question count, but from its 90-minute exam (~35–60 total, ~11–18 in this domain), expect 2–3 from this objective — we provide 27 practice questions to prepare you well beyond it. (estimate)

27questions here

6free pages

7concepts

Questions 1–5

1application · medium
A team has a model endpoint serving version 1 of a model. They have trained a new version (version 2) and want to update the endpoint to serve version 2 without downtime. What should they do?
Select an answer first
2application · medium
A team has a model that requires an environment variable to be set at runtime (e.g., an API key for a downstream service). They want to deploy it to a model endpoint. What should they do?
Select an answer first
3foundation · easy
Which of the following is an example of an endpoint configuration parameter in Databricks?
Select an answer first
4foundation · easy
Which action is part of managing the lifecycle of a model endpoint?
Select an answer first
5foundation · easy
Which scenario best describes the use of a model 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-ASSOCIATE

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-ASSOCIATE” is a trademark of its owner, used for identification only.