AI-900 Practice Question: Describe fundamental principles of machine learning on Azure
What is the difference between a binary classification model and a multi-class classification model?
⚠ Common exam trap
It's easy for candidates to confuse the number of output classes with the type of data or output format, leading them to pick Option A or C, when the core distinction is simply the count of possible prediction outcomes.
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
✓
Binary classification predicts two outcomes; multi-class predicts three or more outcomes
Binary classification models are designed to predict exactly two possible outcomes (e.g., spam/not spam), while multi-class classification models predict three or more mutually exclusive classes (e.g., classifying images of cats, dogs, and birds). In Azure Machine Learning, binary classification algorithms like Logistic Regression output a single probability score, whereas multi-class algorithms like Multinomial Logistic Regression or One-vs-Rest meta-estimators output a probability distribution across all classes.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Binary classification uses numeric outputs; multi-class uses categorical outputs
Why it's wrong here
Binary classification and multi-class classification both produce categorical predictions—each instance is assigned to a discrete class label, such as 'spam' or 'not spam' (binary) or 'cat,' 'dog,' and 'bird' (multi-class). While a binary model may output a single numeric probability via a sigmoid, the underlying target variable is categorical, not numeric. Numeric outputs are characteristic of regression tasks, not classification, so this statement confuses the label type with the output representation.
- ✓
Binary classification predicts two outcomes; multi-class predicts three or more outcomes
Why this is correct
The defining distinction is the number of possible classes in the target variable. Binary classification separates instances into exactly two mutually exclusive outcomes—for instance, 'positive' and 'negative'—while multi-class classification separates them into three or more distinct labels, such as classifying handwritten digits as 0 through 9. This count of the target classes is what determines the classification type, regardless of the algorithm or data modality.
- ✗
Binary is for images; multi-class is for text
Why it's wrong here
Whether a problem is binary or multi-class depends solely on the number of classes in the output label, not on the type of input data. For example, an image classifier may have two classes ('cat' vs. 'dog') making it binary, or several classes ('cat', 'dog', 'bird') making it multi-class; similarly, text classification can be binary ('spam' vs. 'ham') or multi-class ('positive', 'neutral', 'negative'). Thus, images and text can both be used for either classification type, making the statement incorrect.
- ✗
Binary classification is always more accurate than multi-class
Why it's wrong here
Accuracy is not an inherent property of the classification type; it depends on the data, feature engineering, and model tuning, so a binary model is not guaranteed to outperform a multi-class model. This option is tempting because binary problems often have fewer classes, which can reduce ambiguity and sometimes yield higher accuracy in practice, but that is a contingent outcome, not a fixed rule.
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
Regression
Regression is a type of machine learning algorithm that predicts a continuous numeric output based on input data, used to model relationships between variables.
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.