Microsoft Azure AI Fundamentals (AI-900)Describe fundamental principles of machine learning on AzureEasy
A financial institution wants to develop a machine learning model to detect fraudulent transactions. The model needs to classify each transaction as either 'fraudulent' or 'legitimate'. Which type of machine learning problem is this?
- AReinforcement Learning
- BClustering
- CClassification
- DRegression
Show answer & explanationAnswer & explanation
Correct answer: C. Classification
This is a classification problem because the model needs to assign each transaction to one of two predefined categories: 'fraudulent' or 'legitimate'. Classification deals with predicting discrete, categorical outputs.
Why the other options are wrong
- A. Reinforcement Learning involves an agent learning through trial and error with rewards, not directly classifying data.
- B. Clustering groups similar data points without predefined labels, which is unsupervised learning.
- D. Regression predicts continuous numerical values, not discrete categories.
Classification
A supervised machine learning task that involves predicting a discrete, categorical label or class for a given input.
- Output is a category (e.g., spam/not spam, fraudulent/legitimate).
- Requires labeled training data.
- Common algorithms include Logistic Regression, Decision Trees, Support Vector Machines.
Memory trick: Classify 'F' for 'Fraud' into a specific group.