The correct first step is to use oversampling or class-weight techniques to balance the training data. This directly addresses the class imbalance in Azure Custom Vision, where abnormal cases make up only 5% of the dataset, causing the model to bias toward the majority normal class and achieve high accuracy while missing critical abnormal cases. By applying methods like SMOTE for oversampling or adjusting class weights, you force the model to pay more attention to the minority class, which improves recall and reduces false negatives—the core issue behind missed diagnoses. On the AI-102 exam, this scenario tests your understanding that preprocessing to fix imbalance is a prerequisite before tuning hyperparameters or changing algorithms; a common trap is to jump to adjusting the confidence threshold or switching to a different model architecture first. Remember the memory tip: “Balance before you boost”—always correct class distribution before tweaking model settings.
AI-102 Implement computer vision solutions Practice Question
This AI-102 practice question tests your understanding of implement computer vision solutions. The scenario asks you to isolate a root cause — eliminate options that address a different problem before choosing. 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 hospital uses Azure Custom Vision to classify X-ray images as normal or abnormal. The model achieves 98% accuracy on the test set. However, during deployment, the model misclassifies many abnormal cases as normal, causing missed diagnoses. The hospital has a class imbalance where abnormal cases are only 5% of the data. What should the data scientist do first to address this?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue: "first"
Why it matters: Order matters here. You are being tested on which action comes before the others — not which action is generally useful.
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Use oversampling or class-weight techniques to balance the training.
Option D is correct because the primary issue is class imbalance, where abnormal cases constitute only 5% of the data. Oversampling (e.g., SMOTE) or class-weight techniques adjust the training process to give more importance to the minority class, directly addressing the model's bias toward the majority class and reducing false negatives. This is a standard preprocessing step in Custom Vision and other ML frameworks before tuning hyperparameters or changing algorithms.
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.
✗
Increase the number of training epochs.
Why it's wrong here
More epochs may lead to overfitting and not address imbalance.
✗
Add more normal X-ray images to the dataset.
Why it's wrong here
Adding more normal images worsens the imbalance.
✗
Switch to a different object detection algorithm.
Why it's wrong here
The algorithm is not the root cause; imbalance is.
✓
Use oversampling or class-weight techniques to balance the training.
Why this is correct
Balancing the dataset or adjusting loss weights improves minority class recall.
Clue confirmation
The clue word "first" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates often confuse accuracy with model effectiveness, assuming high test accuracy (98%) means the model is robust, but they overlook that accuracy is misleading with severe class imbalance—a model predicting 'normal' for every image would achieve 95% accuracy while missing all abnormal cases.
Detailed technical explanation
How to think about this question
Under the hood, Custom Vision uses transfer learning with a pre-trained CNN (e.g., ResNet) and fine-tunes on the provided dataset. Without class weighting, the default cross-entropy loss treats all samples equally, so the model minimizes overall error by predicting the majority class. Oversampling duplicates minority samples or generates synthetic ones (e.g., via SMOTE), while class-weight techniques scale the loss contribution per sample inversely to class frequency, forcing the model to focus on rare but critical abnormal cases.
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 media company stores terabytes of video archives that are accessed once a year for audit purposes. Moving these objects to a cold storage tier (Azure Archive, S3 Glacier, or Google Nearline) costs a fraction of hot storage. Questions like this test whether you understand storage tiers, access frequency tradeoffs, and retrieval latency requirements.
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.
Implement computer vision solutions — This question tests Implement computer vision solutions — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Use oversampling or class-weight techniques to balance the training. — Option D is correct because the primary issue is class imbalance, where abnormal cases constitute only 5% of the data. Oversampling (e.g., SMOTE) or class-weight techniques adjust the training process to give more importance to the minority class, directly addressing the model's bias toward the majority class and reducing false negatives. This is a standard preprocessing step in Custom Vision and other ML frameworks before tuning hyperparameters or changing algorithms.
What should I do if I get this AI-102 question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Are there clue words in this question I should notice?
Yes — watch for: "first". Order matters here. You are being tested on which action comes before the others — not which action is generally useful.
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 →
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-102 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-102 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.