AI-900 Question 123
Select 3You are working as a data scientist for a retail company and need to build and deploy a machine learning model to predict customer churn. Which Azure Machine Learning capabilities can you use to manage the entire machine learning lifecycle, from data preparation to deployment?
- A
Automated ML for training and hyperparameter tuning
- B
Azure Machine Learning Designer for drag-and-drop model creation
- C
Azure Data Factory for real-time model deployment
- D
Model registry for model versioning and management
- E
Azure Monitor for tracking experiment performance
Show answer and explanation
Correct answers: A, B, D
Explanation
Azure Machine Learning offers several capabilities to support the end-to-end machine learning lifecycle. Automated ML assists with model training and tuning, the Designer enables no-code model creation, and the model registry allows for versioning and deployment management. These capabilities streamline the process of building, deploying, and maintaining machine learning solutions in Azure.
- A. Correct.
Automated ML simplifies the training process by automatically selecting the best model and tuning hyperparameters, making it a key part of the machine learning lifecycle in Azure Machine Learning.
- B. Correct.
Azure Machine Learning Designer provides a no-code environment for building and experimenting with machine learning models, which is useful for data scientists who prefer a visual interface.
- C. Incorrect.
Azure Data Factory is primarily used for data integration and orchestration, not specifically for real-time model deployment.
- D. Correct.
The model registry in Azure Machine Learning helps manage, version, and deploy models, which is essential for maintaining the lifecycle of machine learning projects.
- E. Incorrect.
Azure Monitor is used for general monitoring of Azure resources and applications, but it is not a specific Azure Machine Learning capability.