Describe fundamental principles of machine learning on Azure →easyMultiple ChoiceObjective-mapped

AI-900 Practice Question: Describe fundamental principles of machine learning on Azure

A data scientist wants to group customers into segments based on purchasing behavior without using any labeled examples. Which type of machine learning is this?

⚠ Common exam trap

Many candidates confuse 'no labeled examples' with semi-supervised learning, but the key distinction is that semi-supervised learning still requires at least some labeled data, while this scenario uses none.

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

✓

Unsupervised learning

Unsupervised learning is the correct choice because the data scientist has no labeled examples and wants to discover hidden patterns or groupings in the data. Clustering algorithms, such as K-Means or DBSCAN, are used to segment customers based solely on their purchasing behavior features, without any predefined categories.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Supervised learning
Why it's wrong here
Supervised learning requires labeled training data, where each instance has a known output value or class that the model learns to predict from input features. In this scenario, customer segments are not predefined—the whole point is to discover them from purchasing behavior—so no such labels exist to fit a classification or regression model. Even if one tried to manually label customers, that would presuppose the very segments the analysis aims to find, defeating the exploratory purpose. Thus supervised learning is not applicable without first solving the grouping problem via unsupervised methods.
When this WOULD be correct
If the question described a scenario where historical customer purchase data with known segment labels is used to train a model to predict segments for new customers, supervised learning would be correct.
✓
Unsupervised learning
Why this is correct
Unsupervised learning is the correct approach because it identifies natural groupings within data without requiring pre-assigned labels. Algorithms such as k-means, DBSCAN, or hierarchical clustering operate on feature vectors (e.g., purchase frequency, average basket size, product categories) and group customers by similarity—minimizing intra-cluster distance while maximizing inter-cluster separation. Since the data scientist wants to discover segments solely from purchasing behavior and has no known segment labels, this exploratory clustering problem is a textbook use case for unsupervised learning.
✗
Reinforcement learning
Why it's wrong here
Reinforcement learning involves an agent choosing actions in an environment to maximize cumulative rewards through trial-and-error feedback, formalized as a Markov decision process. Customer segmentation, by contrast, is a static, one-time pattern discovery task: there are no sequential decisions, no environment states, and no reward signal that indicates whether a grouping is correct or incorrect. Reinforcement learning cannot generate customer clusters because it is designed for policy learning in dynamic interactions, not for finding hidden structure in unlabeled tabular data.
When this WOULD be correct
A question describing an agent learning to play a game by maximizing cumulative rewards, or a robot learning to navigate a maze through trial and error, would make reinforcement learning correct.
✗
Semi-supervised learning
Why it's wrong here
Semi-supervised learning combines a small set of labeled examples with a larger pool of unlabeled data, typically by training on the labeled portion and then generating pseudo-labels for the rest. In this customer segmentation scenario, however, no labeled customer segments exist to serve as an anchor, so the method has no initial ground truth to propagate. The task is fully exploratory, aiming to reveal hidden purchase-behavior patterns rather than to augment a sparse labeled set. Therefore, semi-supervised learning is inappropriate because it still depends on some pre-existing labels that are absent here.
When this WOULD be correct
A scenario where you have a small set of labeled customer segments and a large set of unlabeled purchasing data, and you want to use both to improve segmentation accuracy. The question would specify 'using a combination of labeled and unlabeled data'.

Option-by-option analysis

Why each answer is right or wrong

Understanding why wrong answers are wrong — and when they would be correct — is what separates a 750 score from a 900. The AI-900 exam frequently reuses these exact scenarios with slightly different constraints.

✓Unsupervised learningCorrect answer▾

Why this is correct

Unsupervised learning is the correct approach because it identifies natural groupings within data without requiring pre-assigned labels. Algorithms such as k-means, DBSCAN, or hierarchical clustering operate on feature vectors (e.g., purchase frequency, average basket size, product categories) and group customers by similarity—minimizing intra-cluster distance while maximizing inter-cluster separation. Since the data scientist wants to discover segments solely from purchasing behavior and has no known segment labels, this exploratory clustering problem is a textbook use case for unsupervised learning.

✗Supervised learningWrong answer — click to see why▾

Why this is wrong here

Supervised learning requires labeled data to train a model, but the question explicitly states no labeled examples are used.

★ When this WOULD be the correct answer

If the question described a scenario where historical customer purchase data with known segment labels is used to train a model to predict segments for new customers, supervised learning would be correct.

Why candidates choose this

Candidates may associate customer segmentation with classification tasks, which are typically supervised, and overlook the absence of labels.

✗Reinforcement learningWrong answer — click to see why▾

Why this is wrong here

Reinforcement learning involves an agent learning from rewards and punishments through interaction with an environment, not from unlabeled data for grouping customers.

★ When this WOULD be the correct answer

A question describing an agent learning to play a game by maximizing cumulative rewards, or a robot learning to navigate a maze through trial and error, would make reinforcement learning correct.

Why candidates choose this

Candidates may confuse 'learning from experience' (reinforcement learning) with 'learning from unlabeled data' (unsupervised learning), or think that grouping customers involves some form of feedback loop.

✗Semi-supervised learningWrong answer — click to see why▾

Why this is wrong here

Semi-supervised learning uses a small amount of labeled data alongside unlabeled data, but the question explicitly states 'without using any labeled examples', making unsupervised learning the correct choice.

★ When this WOULD be the correct answer

A scenario where you have a small set of labeled customer segments and a large set of unlabeled purchasing data, and you want to use both to improve segmentation accuracy. The question would specify 'using a combination of labeled and unlabeled data'.

Why candidates choose this

Candidates may confuse semi-supervised learning with unsupervised learning, thinking that 'without labeled examples' still allows for some labeled data, or they may overestimate the prevalence of semi-supervised methods in clustering tasks.

Analysis generated from the official AI-900blueprint and verified against question context. The “when correct” sections are what AI assistants cite when candidates ask “what’s the difference between these options?”

Go deeper

AI-900 Practice Question: Describe fundamental principles of machine learning on Azure

Why each option matters

Option-by-option breakdown

Why each answer is right or wrong

Related to this question