Microsoft Azure AI Fundamentals (AI-900)Describe fundamental principles of machine learning on AzureMedium
A financial institution wants to develop a machine learning model to predict whether a loan applicant will default on their loan. The model will analyze various features such as credit score, income, and debt-to-income ratio. The output of the model needs to be a clear 'Yes' or 'No' decision regarding default. Which type of machine learning task best fits this scenario?
- AReinforcement Learning
- BClustering
- CRegression
- DClassification
Show answer & explanationAnswer & explanation
Correct answer: D. Classification
The problem requires the model to predict a discrete category ('Yes' or 'No' default), which is the definition of a classification task. Regression predicts continuous values, clustering groups data without labels, and reinforcement learning involves agents learning through rewards.
Why the other options are wrong
- A. Reinforcement Learning involves an agent learning actions in an environment through trial and error, not predicting discrete outcomes from input data.
- B. Clustering is an unsupervised learning technique used to group similar data points without predefined labels.
- C. Regression predicts continuous numerical values, not discrete categories like 'Yes' or 'No'.
Classification
A supervised machine learning task where the model learns to predict a discrete category or class label for new input data.
- Output is a discrete value (e.g., 'spam'/'not spam', 'cat'/'dog', 'yes'/'no').
- Requires labeled training data.
- Common algorithms include Logistic Regression, Support Vector Machines, Decision Trees.
Memory trick: Learning with a teacher to hit the bullseye.