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

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

An online retailer wants to build a recommendation system that learns from user interactions. The system suggests a product, and if the user clicks it, it receives a positive reward; if ignored, a negative reward. Over time, the system learns to make better suggestions. Which type of machine learning best describes this approach?

⚠ Common exam trap

Test-takers frequently confuse reinforcement learning with supervised learning because both involve feedback, but reinforcement learning uses evaluative feedback (rewards) rather than instructive feedback (labeled examples).

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

✓

Reinforcement learning

Reinforcement learning is correct because the system learns by interacting with its environment (user clicks) and receiving rewards (positive for clicks, negative for ignores) to maximize cumulative reward over time. This trial-and-error feedback loop, without explicit labeled data, is the hallmark of reinforcement learning.

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 trains on labeled data where the correct output is known. In this scenario, there is no pre-labeled 'correct recommendation'; the system learns from delayed feedback, not from a training set of correct examples.
When this WOULD be correct
A question describing a system that predicts whether a user will click a product based on historical labeled data (e.g., past clicks and non-clicks) would make supervised learning correct, as it uses input-output pairs to learn a mapping.
✗
Unsupervised learning
Why it's wrong here
Unsupervised learning is incorrect because it seeks to discover hidden structure, such as clusters or latent factors, from unlabeled data without any feedback signal. A recommendation system that learns which item to show next from click rewards is explicitly optimizing an action-value function guided by scalar rewards, not merely finding patterns in item or user features. Unsupervised methods like k-means or matrix factorization can preprocess user data, but they cannot replace the reward-driven sequential decision-making described in the scenario.
When this WOULD be correct
A question describes a system that groups products into categories based on purchase history without any labeled outcomes or reward signals, such as 'Which ML type is used to segment customers into clusters based on buying behavior?'
✓
Reinforcement learning
Why this is correct
Reinforcement learning fits because the retailer's recommendation system is an agent that selects items to present (actions) to users (the environment) and observes engagement signals such as clicks as rewards. The agent's objective is to maximize cumulative reward over time by learning a policy that maps user state to optimal recommendations. This trial-and-error learning from delayed feedback—rather than from a fixed labeled dataset—is the defining characteristic of an RL problem.
✗
Semi-supervised learning
Why it's wrong here
Semi-supervised learning assumes a training corpus that combines a small set of labeled examples with a larger set of unlabeled examples, where labels are the known correct outputs. Here, there is no labeled dataset of 'correct recommendations' to bootstrap from; instead, the system receives only delayed reward signals after taking actions. Semi-supervised methods would still require some ground-truth labels, which are absent in this interaction-driven setting, so this option does not describe the mechanism.
When this WOULD be correct
A scenario where a company has a small set of customer purchase histories (labeled) and a large set of browsing data (unlabeled) and wants to predict purchase intent. Semi-supervised learning would leverage both to improve accuracy.

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.

✓Reinforcement learningCorrect answer▾

Why this is correct

Reinforcement learning fits because the retailer's recommendation system is an agent that selects items to present (actions) to users (the environment) and observes engagement signals such as clicks as rewards. The agent's objective is to maximize cumulative reward over time by learning a policy that maps user state to optimal recommendations. This trial-and-error learning from delayed feedback—rather than from a fixed labeled dataset—is the defining characteristic of an RL problem.

✗Supervised learningWrong answer — click to see why▾

Why this is wrong here

The system learns from rewards and penalties based on its actions (suggesting products) without explicit labeled examples, which is characteristic of reinforcement learning, not supervised learning.

★ When this WOULD be the correct answer

A question describing a system that predicts whether a user will click a product based on historical labeled data (e.g., past clicks and non-clicks) would make supervised learning correct, as it uses input-output pairs to learn a mapping.

Why candidates choose this

Candidates may think the positive/negative feedback resembles labeled data, but in reinforcement learning the feedback is evaluative (reward) rather than instructive (correct label), and the agent learns through trial and error.

✗Unsupervised learningWrong answer — click to see why▾

Why this is wrong here

Unsupervised learning finds hidden patterns in unlabeled data without explicit feedback, but this system learns from positive/negative rewards based on user clicks, which is a hallmark of reinforcement learning.

★ When this WOULD be the correct answer

A question describes a system that groups products into categories based on purchase history without any labeled outcomes or reward signals, such as 'Which ML type is used to segment customers into clusters based on buying behavior?'

Why candidates choose this

Candidates may think the system 'learns on its own' from user interactions without labeled data, confusing the absence of explicit labels with unsupervised learning, while missing the reward-based 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 with a large amount of unlabeled data, but the scenario describes learning from rewards (positive/negative feedback) without explicit labeled examples, which is characteristic of reinforcement learning.

★ When this WOULD be the correct answer

A scenario where a company has a small set of customer purchase histories (labeled) and a large set of browsing data (unlabeled) and wants to predict purchase intent. Semi-supervised learning would leverage both to improve accuracy.

Why candidates choose this

Candidates may confuse the use of feedback (positive/negative reward) with labeled data, thinking the system is 'semi-supervised' because it receives some signal but not full labels.

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