Microsoft Azure AI Fundamentals (AI-900) Practice Exam

What type of machine learning is exemplified by a banking system predicting loan repayment?

1. Regression

2. Classification

3. Clustering

4. Anomaly detection

The correct answer is: Classification

The scenario of a banking system predicting loan repayment is an example of classification in machine learning. In this type of problem, the goal is to determine which category or class an entity belongs to based on its features. In this case, the bank is trying to classify whether a borrower will repay their loan on time or default, which typically involves binary outcomes: "will repay" or "will not repay." Classification models use labeled training data, where past loan repayment behavior is analyzed to learn the patterns associated with different borrower profiles. After the model is trained, it can predict the likelihood of future borrowers falling into these predefined categories based on their characteristics. This is fundamental to making informed lending decisions and managing financial risk effectively. Other options such as regression, clustering, and anomaly detection do not suit this scenario. Regression is typically used for predicting continuous outcomes; clustering is about grouping unlabelled data into similar categories without predefined labels; and anomaly detection focuses on identifying unusual patterns that do not conform to expected behavior. Each of these methods serves different purposes in the realm of machine learning but doesn’t align with the specific task of predicting loan repayment outcomes.