AI-900 Practice Question: Describe fundamental principles of machine learning on Azure
An e-commerce company has a dataset of customer purchase histories with no predefined categories. The data analyst wants to identify natural groupings of customers based on their purchasing behavior to target marketing campaigns. Which type of machine learning should the analyst use?
⚠ Common exam trap
Watch out — candidates often confuse clustering with classification because both involve grouping, but clustering is unsupervised (no labels) while classification is supervised (requires labeled data).
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Clustering
Clustering is the correct choice because it is an unsupervised learning technique used to discover inherent groupings in data without predefined labels. In this scenario, the analyst wants to identify natural customer segments based on purchase behavior, which aligns perfectly with clustering algorithms like K-Means or DBSCAN that partition data into clusters of similar patterns.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Regression
Why it's wrong here
Regression predicts a continuous numerical output, such as a customer's lifetime value or average order amount, based on input features. In a customer purchase dataset without labeled segments, regression cannot assign individuals to discrete groups or clusters because its model output is a numeric scalar, not a membership indicator. Therefore, regression is not appropriate for discovering unknown customer segments.
- ✗
Classification
Why it's wrong here
Classification requires a labeled training set with predefined classes, such as 'high-value' or 'low-value' customers, to learn a decision boundary. The scenario provides only purchase history with no pre-existing customer segment labels, so a classifier cannot be trained or evaluated meaningfully. Since the goal is to discover hidden groupings rather than predict a known label, classification is not the correct approach.
- ✓
Clustering
Why this is correct
Clustering is an unsupervised machine learning technique that groups unlabeled data points based on feature similarity, making it ideal for customer segmentation. Algorithms like K-means partition customers into clusters where those with similar purchase frequency, recency, and monetary value are grouped together, revealing actionable segments without requiring predefined labels. This directly matches the e-commerce goal of identifying distinct customer segments from raw purchase data.
- ✗
Reinforcement learning
Why it's wrong here
Reinforcement learning involves an agent interacting with an environment, taking actions, and learning from rewards or penalties to maximize cumulative return over time. It is designed for sequential decision-making problems, such as dynamic pricing or recommendation policies, not for grouping a static dataset of customer purchases into meaningful segments. Since there is no sequential interaction or reward signal in the given batch purchase data, reinforcement learning is not applicable.
Go deeper
Related to this question
Learn chapter
Machine Learning Core Concepts
Key term
Machine learning
Machine learning is a branch of artificial intelligence where computers learn patterns from data to make decisions or predictions without being explicitly programmed for every task.
Key term
Unsupervised learning
Unsupervised learning is a type of machine learning where an algorithm finds patterns, groupings, or structure in data without being given labeled examples or correct answers.
About these practice questions
This AI-900 question is part of Courseiva's 985-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.