Principal Component Analysis (PCA) is the correct technique for reducing 100 features while retaining maximum variance. PCA works by transforming the original features into a new set of uncorrelated principal components, each capturing a decreasing amount of the dataset’s total variance; by selecting only the top components—say, the first 20—you preserve the most informative structure while drastically cutting dimensionality. On the AI-900 exam, this question tests your understanding of unsupervised dimensionality reduction versus feature selection methods like filter-based or wrapper approaches—a common trap is confusing PCA with feature elimination, but PCA creates new composite features rather than simply dropping existing ones. The exam expects you to recognize that PCA directly addresses the twin goals of speeding up training and reducing overfitting by removing noise and redundancy. Memory tip: think of PCA as “Projecting Components that Accumulate variance”—the first component captures the most spread, so you keep the top ones to retain the big picture.
AI-900 Practice Question: Describe fundamental principles of machine learning on Azure
This AI-900 practice question tests your understanding of describe fundamental principles of machine learning on azure. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. A key principle to apply: pCA is an unsupervised dimensionality reduction technique.. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A data scientist has a dataset with 100 features and 10,000 samples. They want to reduce the number of features while retaining as much variance as possible, to improve model training speed and reduce overfitting. Which technique should they use?
Why wrong: Feature scaling normalizes the range of features but does not reduce the number of features.
B
Principal Component Analysis (PCA)
PCA reduces the dimensionality by projecting data onto principal components, retaining the most variance.
C
Regularization
Why wrong: Regularization techniques like Lasso can shrink coefficients to zero, effectively performing feature selection, but the scenario asks for reducing the number of features explicitly, which PCA directly does.
D
Cross-validation
Why wrong: Cross-validation is used to evaluate model performance, not to reduce the number of features.
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Principal Component Analysis (PCA)
Principal Component Analysis (PCA) is an unsupervised dimensionality reduction technique that transforms the original features into a new set of orthogonal components, ordered by the amount of variance they capture. By selecting only the top principal components, the data scientist can significantly reduce the feature count (e.g., from 100 to 20) while retaining the majority of the dataset's variance, which directly improves model training speed and reduces overfitting.
Key principle: PCA is an unsupervised dimensionality reduction technique.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
Feature scaling
Why it's wrong here
Feature scaling normalizes the range of features but does not reduce the number of features.
✓
Principal Component Analysis (PCA)
Why this is correct
PCA reduces the dimensionality by projecting data onto principal components, retaining the most variance.
Related concept
PCA is an unsupervised dimensionality reduction technique.
✗
Regularization
Why it's wrong here
Regularization techniques like Lasso can shrink coefficients to zero, effectively performing feature selection, but the scenario asks for reducing the number of features explicitly, which PCA directly does.
✗
Cross-validation
Why it's wrong here
Cross-validation is used to evaluate model performance, not to reduce the number of features.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates often confuse regularization (which reduces overfitting by shrinking coefficients) with dimensionality reduction, or they think feature scaling alone can reduce feature count, when PCA is the correct technique for explicitly reducing the number of features while preserving variance.
Trap categories for this question
Scenario analysis trap
Regularization techniques like Lasso can shrink coefficients to zero, effectively performing feature selection, but the scenario asks for reducing the number of features explicitly, which PCA directly does.
Detailed technical explanation
How to think about this question
PCA works by computing the covariance matrix of the data, then performing eigenvalue decomposition to extract eigenvectors (principal components) and eigenvalues that quantify the variance explained by each component. In practice, the explained variance ratio can be plotted to determine the optimal number of components (e.g., retaining 95% of variance), and PCA assumes linear relationships among features, so it may underperform on highly nonlinear data where techniques like t-SNE or autoencoders might be more appropriate.
KKey Concepts to Remember
PCA is an unsupervised dimensionality reduction technique.
PCA transforms data into a new set of orthogonal principal components.
Principal components are ordered by the amount of variance they explain.
PCA helps reduce overfitting and improve model training speed.
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
PCA is an unsupervised dimensionality reduction technique.
Real-world example
How this comes up in practice
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. PCA is an unsupervised dimensionality reduction technique. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
Related glossary terms
Concepts from this question explained
These glossary pages explain the core terms tested in this AI-900 question in full detail.
Describe fundamental principles of machine learning on Azure — This question tests Describe fundamental principles of machine learning on Azure — PCA is an unsupervised dimensionality reduction technique..
What is the correct answer to this question?
The correct answer is: Principal Component Analysis (PCA) — Principal Component Analysis (PCA) is an unsupervised dimensionality reduction technique that transforms the original features into a new set of orthogonal components, ordered by the amount of variance they capture. By selecting only the top principal components, the data scientist can significantly reduce the feature count (e.g., from 100 to 20) while retaining the majority of the dataset's variance, which directly improves model training speed and reduces overfitting.
What should I do if I get this AI-900 question wrong?
Review pCA is an unsupervised dimensionality reduction technique., then practise related AI-900 questions on the same topic to reinforce the concept.
What is the key concept behind this question?
PCA is an unsupervised dimensionality reduction technique.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
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.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.