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

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

A data scientist is training a model to classify customer reviews as positive, negative, or neutral. The dataset contains 10,000 reviews, but only 500 of them are negative. The data scientist wants to ensure the model performs well on the minority class (negative reviews). Which technique should the data scientist consider to address the class imbalance?

⚠ Common exam trap

Test-takers frequently confuse regularization or feature engineering techniques with data-level imbalance solutions, or assume that simply increasing the learning rate can compensate for a skewed dataset.

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

✓

Use a resampling technique like SMOTE or random oversampling of the minority class

Resampling techniques like SMOTE (Synthetic Minority Oversampling Technique) or random oversampling directly address class imbalance by generating synthetic samples or duplicating existing samples from the minority class (negative reviews). This balances the training dataset, preventing the model from being biased toward the majority class (positive/neutral reviews) and improving recall for the minority class.

Answer analysis

Option-by-option breakdown

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

✗
Increase the learning rate
Why it's wrong here
Increasing the learning rate changes only the step size used during gradient descent optimization, not the underlying class distribution. A larger learning rate can cause the model's weight updates to overshoot the optimal parameters, leading to divergent training and worse convergence. Even with a carefully tuned learning rate, the model remains prone to treating the majority class as the dominant pattern, so the imbalance problem persists.
When this WOULD be correct
When training a deep learning model that converges too slowly due to a small learning rate, and the goal is to speed up convergence without causing instability, increasing the learning rate (within a reasonable range) can be correct.
✗
Add more features to the model
Why it's wrong here
Adding more features alters the feature space but leaves the ratio of minority to majority class samples unchanged. This can actually worsen the problem by increasing model complexity and introducing noise or redundant predictors, which may encourage overfitting to the majority class. The classifier still lacks sufficient examples of the minority class to learn its decision boundary reliably.
When this WOULD be correct
If the model underfits due to insufficient predictive information, adding relevant features can improve performance. For example, when training a model to predict house prices with only the number of bedrooms, adding features like square footage and location would be correct.
✓
Use a resampling technique like SMOTE or random oversampling of the minority class
Why this is correct
Resampling techniques directly address the imbalanced class distribution by modifying the training set rather than the model's hyperparameters. SMOTE generates synthetic examples of the minority class through interpolation between existing minority instances, while random oversampling duplicates minority samples to increase their representation. This rebalancing gives the model more exposure to the minority class during training, which typically boosts recall and reduces bias toward the majority class.
✗
Use L1 regularization (Lasso)
Why it's wrong here
L1 regularization, also known as Lasso, adds a penalty proportional to the absolute value of the model coefficients, driving some weights to zero and serving as an embedded feature selection method. It is designed to combat overfitting and improve generalization by enforcing sparsity, but it does nothing to rebalance class frequencies or change the loss landscape's sensitivity to the majority class. The model will still see far more majority examples, so its predictions remain skewed regardless of regularization.
When this WOULD be correct
A question where a model is overfitting due to many irrelevant features, and the goal is to perform feature selection to improve generalization. For example: 'A model has 1000 features but only 50 are relevant. Which technique reduces overfitting by shrinking some coefficients to zero?'

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.

✓Use a resampling technique like SMOTE or random oversampling of the minority classCorrect answer▾

Why this is correct

Resampling techniques directly address the imbalanced class distribution by modifying the training set rather than the model's hyperparameters. SMOTE generates synthetic examples of the minority class through interpolation between existing minority instances, while random oversampling duplicates minority samples to increase their representation. This rebalancing gives the model more exposure to the minority class during training, which typically boosts recall and reduces bias toward the majority class.

✗Increase the learning rateWrong answer — click to see why▾

Why this is wrong here

Increasing the learning rate does not address class imbalance; it controls the step size during gradient descent and can cause the model to converge poorly or diverge, especially with imbalanced data.

★ When this WOULD be the correct answer

When training a deep learning model that converges too slowly due to a small learning rate, and the goal is to speed up convergence without causing instability, increasing the learning rate (within a reasonable range) can be correct.

Why candidates choose this

Candidates may think that a higher learning rate helps the model 'learn faster' from the minority class, but they overlook that learning rate affects optimization, not data distribution.

✗Add more features to the modelWrong answer — click to see why▾

Why this is wrong here

Adding more features does not address class imbalance; it may introduce noise or irrelevant information, potentially worsening model performance on the minority class.

★ When this WOULD be the correct answer

If the model underfits due to insufficient predictive information, adding relevant features can improve performance. For example, when training a model to predict house prices with only the number of bedrooms, adding features like square footage and location would be correct.

Why candidates choose this

Candidates may think that more features provide more information to help the model distinguish the minority class, but this does not solve the core issue of skewed class distribution.

✗Use L1 regularization (Lasso)Wrong answer — click to see why▾

Why this is wrong here

L1 regularization (Lasso) is used to prevent overfitting by penalizing large coefficients, not to address class imbalance. It does not increase the representation of the minority class or adjust the training process to focus on negative reviews.

★ When this WOULD be the correct answer

A question where a model is overfitting due to many irrelevant features, and the goal is to perform feature selection to improve generalization. For example: 'A model has 1000 features but only 50 are relevant. Which technique reduces overfitting by shrinking some coefficients to zero?'

Why candidates choose this

Candidates may confuse regularization with techniques that handle imbalance, thinking that penalizing complexity somehow helps the minority class, or they recall that L1 can be used for feature selection but misapply it to this context.

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