Question 3
Domain 2: Describe fundamental principles of machine learning on AzureWhen creating a machine learning model for predicting customer churn, which type of model would you use?
Correct answer: A
Explanation
Classification is used when the target outcome is a discrete category, such as whether a customer will churn or not. Churn prediction assigns each customer to one of a limited set of labels, so the model learns to predict class membership rather than a continuous value.
Why each option is right or wrong
A. Classification
Churn prediction asks the model to assign each customer to one of two discrete labels: churn or not churn, which makes it a supervised classification task rather than a regression problem. In standard ML practice, binary classification is used whenever the dependent variable is categorical with a finite set of outcomes, and the model typically outputs a class label or probability for each class.
B. Regression
C. Clustering
D. Anomaly Detection