AI-900 Question 79
Select 4You are tasked with building a machine learning model on Azure to predict customer churn for a subscription-based service. You want to use Azure Machine Learning and follow the basic principles of machine learning. Which steps should you include in your workflow?
- A
Define the business problem and identify the data needed.
- B
Use Azure Resource Manager templates to deploy the model directly.
- C
Split the dataset into training and testing data.
- D
Train the model using labeled data to optimize its performance.
- E
Evaluate the model's performance using appropriate metrics.
Show answer and explanation
Correct answers: A, C, D, E
Explanation
The fundamental principles of machine learning on Azure include defining the problem, preparing the data, training the model, and evaluating its performance. These steps are critical in ensuring a successful machine learning workflow. Azure Resource Manager templates, while useful for resource management, are unrelated to the machine learning process.
- A. Correct.
Defining the business problem and identifying the data is the initial step in any machine learning workflow. It ensures that the problem and goals are clearly understood.
- B. Incorrect.
Azure Resource Manager templates are used for infrastructure deployment, not for building or training machine learning models. This is not a part of the machine learning workflow.
- C. Correct.
Splitting the dataset into training and testing partitions is critical to ensure the model is trained properly and its performance can be evaluated fairly.
- D. Correct.
Training the model using labeled data is a fundamental step in supervised machine learning, which is likely used for a churn prediction task.
- E. Correct.
Evaluating the model's performance using appropriate metrics ensures that the model meets the required accuracy or effectiveness standards.