Databricks-ML-Assoc Model Deployment Practice Question
A data scientist registers a scikit-learn model in Unity Catalog as `prod.ml.churn_model`. They then create a Databricks Model Serving endpoint via the REST API using `served_entities` with `entity_name` set to `prod.ml.churn_model` and `entity_version` set to `"3"`. The endpoint creation fails. What is the most likely cause?
⚠ Common exam trap
The trap here is assuming that a user who can view a Unity Catalog model in the UI automatically has the EXECUTE privilege required for Model Serving to load the artifacts.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
The serving endpoint lacks USE CATALOG, USE SCHEMA, and EXECUTE privileges on the Unity Catalog model, so the service principal cannot read the model artifacts.
Serving a Unity Catalog model requires the serving identity to hold USE CATALOG, USE SCHEMA, and EXECUTE privileges on the catalog, schema, and model. Without these grants, the endpoint cannot retrieve the model version, and creation fails. Referencing the model by three-level name and version string is otherwise correct, so permissions are the most likely root cause.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Model Serving only supports models registered in the workspace Model Registry, not models registered in Unity Catalog.
Why it's wrong here
Databricks Model Serving fully supports Unity Catalog models using the three-level namespace in `entity_name`. Both workspace Model Registry and Unity Catalog registries can back a serving endpoint, with Unity Catalog being the recommended approach for governance. This misconception about registry compatibility is incorrect and does not explain the failure in this scenario.
- ✗
The model version must be referenced as a numeric integer, but the field only accepts a string, so the deployment cannot resolve the artifact path.
Why it's wrong here
Databricks Model Serving expects `entity_version` as a string because Unity Catalog model versions are stored as string identifiers in the serving configuration schema. Supplying a string is correct, not the cause of failure. The failure in this scenario stems from something else in the configuration, such as missing serving permissions or an invalid workload specification, not the data type of the version field.
- ✗
The model must first be exported to DBFS as an MLflow artifact tarball before it can be referenced by a serving endpoint.
Why it's wrong here
Unity Catalog models are referenced directly by three-level namespace; no manual export to DBFS is needed. Databricks Model Serving resolves artifacts from the Unity Catalog model version storage location automatically. This extra export step would be redundant and is not part of the supported deployment workflow, so it cannot explain the endpoint creation failure.
- ✓
The serving endpoint lacks USE CATALOG, USE SCHEMA, and EXECUTE privileges on the Unity Catalog model, so the service principal cannot read the model artifacts.
Why this is correct
Databricks Model Serving authenticates as a platform-managed identity and requires explicit Unity Catalog grants on the model's parent catalog, schema, and the model itself. Without USE CATALOG, USE SCHEMA, and EXECUTE on `prod.ml.churn_model`, the endpoint cannot fetch artifacts and creation fails. Granting these to the serving identity or the requesting user resolves the deployment.
About these practice questions
Courseiva writes every Databricks-ML-Assoc question from scratch — 319 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Databricks exam blueprint
This Databricks-ML-Assoc practice question is part of Courseiva's free Databricks certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the Databricks-ML-Assoc exam.