Designing and Implementing a Data Science Solution on Azure — Question 162

You manage an Azure Machine Learning workspace.

An MLflow model is already registered. You plan to customize how the deployment does inference.

You need to deploy the MLflow model to a batch endpoint for batch inferencing.

What should you create first?

Answer options

• A. scoring script
• B. deployment
• C. environment
• D. deployment definition

Correct answer: A

Explanation

The correct first step is to create a scoring script (A), as it defines how the model will process input data for batch inference. Without this script, the deployment cannot know how to handle the incoming data. The other options, such as deployment (B), environment (C), and deployment definition (D), are relevant but depend on having a scoring script in place first.