- A
Apply L1 regularization (Lasso) to the model
L1 regularization adds a penalty term that can zero out coefficients of less important features, performing feature selection and reducing model complexity to combat overfitting.
- B
Apply L2 regularization (Ridge) to the model
Why wrong: L2 regularization penalizes large coefficients but does not eliminate features entirely; it shrinks coefficients but keeps them non-zero, which may not sufficiently reduce complexity when many irrelevant features are present.
- C
Use k-fold cross-validation to select the best model
Why wrong: Cross-validation is a technique for evaluating model performance and tuning hyperparameters, but it does not directly reduce overfitting or eliminate features. It would need to be combined with a regularized model.
- D
Increase the number of training samples by data augmentation
Why wrong: Data augmentation is common for image or text data, but for structured churn data with 200 features, creating realistic synthetic samples is complex and not a standard direct approach to reduce overfitting.
Quick Answer
The answer is L1 regularization (Lasso) because it applies a penalty equal to the absolute value of the coefficients, which can shrink irrelevant feature weights exactly to zero, performing automatic feature selection. This directly addresses the overfitting described—where 200 features on only 500 records cause the model to memorize noise rather than learn general patterns. On the Microsoft Azure AI Fundamentals AI-900 exam, this scenario tests your understanding of how L1 regularization differs from L2 (Ridge), which reduces coefficients but never eliminates them entirely. A common trap is choosing L2 regularization, thinking any penalty will help, but only L1 removes features entirely. Remember the mnemonic: L1 can "Lasso" and eliminate, while L2 can only "Ridge" and reduce.
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. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. 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 is training a logistic regression model to predict customer churn using a small dataset with 500 records and 200 features. The model achieves 97% accuracy on the training set but only 65% on a held-out test set, indicating severe overfitting. The data scientist wants to reduce overfitting by automatically eliminating irrelevant features. Which technique should the data scientist apply?
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
Apply L1 regularization (Lasso) to the model
L1 regularization (Lasso) adds a penalty equal to the absolute value of the magnitude of coefficients, which can shrink some coefficients exactly to zero. This performs automatic feature selection by eliminating irrelevant features, directly addressing the overfitting caused by having 200 features on only 500 records. The high training accuracy (97%) versus low test accuracy (65%) is a classic sign of overfitting that L1 regularization mitigates by reducing model complexity.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Apply L1 regularization (Lasso) to the model
Why this is correct
L1 regularization adds a penalty term that can zero out coefficients of less important features, performing feature selection and reducing model complexity to combat overfitting.
Related concept
Read the scenario before looking for a memorised answer.
- ✗
Apply L2 regularization (Ridge) to the model
Why it's wrong here
L2 regularization penalizes large coefficients but does not eliminate features entirely; it shrinks coefficients but keeps them non-zero, which may not sufficiently reduce complexity when many irrelevant features are present.
- ✗
Use k-fold cross-validation to select the best model
Why it's wrong here
Cross-validation is a technique for evaluating model performance and tuning hyperparameters, but it does not directly reduce overfitting or eliminate features. It would need to be combined with a regularized model.
- ✗
Increase the number of training samples by data augmentation
Why it's wrong here
Data augmentation is common for image or text data, but for structured churn data with 200 features, creating realistic synthetic samples is complex and not a standard direct approach to reduce overfitting.
Common exam traps
Common exam trap: answer the scenario, not the keyword
Microsoft often tests the distinction between L1 and L2 regularization: the trap here is that candidates confuse 'reducing overfitting' (which both can do) with 'eliminating features' (which only L1 does), leading them to pick L2 regularization or cross-validation instead.
Detailed technical explanation
How to think about this question
L1 regularization modifies the loss function by adding λ∑|wᵢ|, where λ controls the penalty strength; during optimization, this creates a diamond-shaped constraint region that often forces coefficients to hit the axes, yielding sparse models. In contrast, L2 regularization uses λ∑wᵢ², producing a circular constraint that rarely zeroes out coefficients. For high-dimensional datasets with many irrelevant features (200 features, 500 samples), L1 is preferred because it performs embedded feature selection, reducing the risk of overfitting by removing noise features entirely.
KKey Concepts to Remember
- Read the scenario before looking for a memorised answer.
- Find the constraint that changes the correct option.
- Eliminate answers that are true in general but not in this case.
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
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A company's IT admin needs to give a contractor read-only access to production logs without sharing account credentials. Using role-based access control (RBAC) and temporary scoped permissions — not a permanent shared password — is the correct pattern. Questions like this test whether you can apply least-privilege access across cloud identity services.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
- →
Describe fundamental principles of machine learning on Azure — study guide chapter
Learn the concepts, then practise the questions
- →
Describe fundamental principles of machine learning on Azure practice questions
Targeted practice on this topic area only
- →
All AI-900 questions
1,020 questions across all exam domains
- →
Microsoft Azure AI Fundamentals AI-900 study guide
Full concept coverage aligned to exam objectives
- →
AI-900 practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related AI-900 practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Describe Artificial Intelligence workloads and considerations practice questions
Practise AI-900 questions linked to Describe Artificial Intelligence workloads and considerations.
Describe fundamental principles of machine learning on Azure practice questions
Practise AI-900 questions linked to Describe fundamental principles of machine learning on Azure.
Describe features of computer vision workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of computer vision workloads on Azure.
Describe features of Natural Language Processing workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of Natural Language Processing workloads on Azure.
Describe features of generative AI workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of generative AI workloads on Azure.
AI-900 fundamentals practice questions
Practise AI-900 questions linked to AI-900 fundamentals.
AI-900 scenario practice questions
Practise AI-900 questions linked to AI-900 scenario.
AI-900 troubleshooting practice questions
Practise AI-900 questions linked to AI-900 troubleshooting.
Practice this exam
Start a free AI-900 practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this AI-900 question test?
Describe fundamental principles of machine learning on Azure — This question tests Describe fundamental principles of machine learning on Azure — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Apply L1 regularization (Lasso) to the model — L1 regularization (Lasso) adds a penalty equal to the absolute value of the magnitude of coefficients, which can shrink some coefficients exactly to zero. This performs automatic feature selection by eliminating irrelevant features, directly addressing the overfitting caused by having 200 features on only 500 records. The high training accuracy (97%) versus low test accuracy (65%) is a classic sign of overfitting that L1 regularization mitigates by reducing model complexity.
What should I do if I get this AI-900 question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
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 →
Same concept, more angles
3 more ways this is tested on AI-900
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A data scientist is training a regression model to predict energy consumption. The dataset includes features like temperature, humidity, time of day, and day of week. After training, the model performs well on the training set but poorly on new data. Which approach would most likely help reduce this problem?
medium- A.Add more features to the model.
- ✓ B.Use a simpler model with fewer parameters.
- C.Increase the number of training epochs.
- D.Use a more complex model to capture more patterns.
Why B: The model performs well on the training set but poorly on new data, which is classic overfitting. Using a simpler model with fewer parameters reduces the model's capacity to memorize noise and irrelevant patterns, forcing it to learn the underlying generalizable relationships. This directly addresses the variance problem without requiring additional data or computational resources.
Variation 2. A data scientist trains a regression model to predict energy consumption for a smart building. The model achieves very low error on the training data but performs significantly worse on a held-out validation set. Which technique would most directly address this problem?
hard- A.Feature engineering
- ✓ B.Regularization
- C.Cross-validation
- D.Hyperparameter tuning
Why B: The model's low training error but high validation error indicates overfitting, where the model has memorized the training data rather than learning generalizable patterns. Regularization (e.g., L1 or L2) directly penalizes large coefficients, reducing model complexity and improving generalization to unseen data.
Variation 3. A data scientist trains a decision tree model to predict customer churn. The model achieves 99% accuracy on the training data but only 80% on the test data. Which concept best explains this performance difference?
medium- A.Underfitting
- ✓ B.Overfitting
- C.Bias-variance tradeoff
- D.Cross-validation
Why B: The model's high accuracy on training data (99%) but significantly lower accuracy on test data (80%) indicates that it has memorized the training data rather than learning generalizable patterns. This is the classic symptom of overfitting, where the decision tree captures noise and outliers in the training set, leading to poor performance on unseen data.
Last reviewed: Jun 30, 2026
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.