The answer is recall. In an imbalanced dataset like this one, where defective parts make up only 2% of the data, accuracy is misleading because a model that predicts everything as “non-defective” still scores 98% accuracy while failing to catch any actual defects. Recall, also known as sensitivity, measures the proportion of true positives correctly identified out of all actual positives, so it drops to 0% here—directly exposing the model’s inability to detect defective parts. On the Microsoft Azure AI Fundamentals AI-900 exam, this scenario tests your understanding of why recall is the best metric for imbalanced classification, often appearing in questions about manufacturing or fraud detection where false negatives are costly. A common trap is choosing accuracy, which looks good but hides model failure. To remember: recall is about “catching the rare ones”—think of it as the “catch rate” for the minority class.
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 manufacturer trains a model to detect defective parts on an assembly line. Only 2% of parts are defective. The model predicts 'non-defective' for all parts and achieves 98% accuracy. Which metric best reveals the model's inability to identify defective parts?
Clue words in this question
Noticing these words before you look at the options changes how you read each choice.
Clue: "best"
Why it matters: Signals that multiple options may be partially correct. Choose the option that most directly solves the exact problem described, not the one that sounds most complete.
Why wrong: Accuracy is 98% in this case, which seems good but hides the model's failure to detect any defective parts.
B
Precision
Why wrong: Precision measures how many predicted defective parts are actually defective. Since no parts are predicted defective, precision is undefined or 0, but recall is a more direct indicator of missing positives.
C
Recall
Recall (sensitivity) is the proportion of actual defective parts that the model correctly identifies. A recall of 0% clearly shows the model fails to detect any defects.
D
F1 Score
Why wrong: F1 Score is the harmonic mean of precision and recall. It would be 0, but recall directly reveals the issue without combining with precision.
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Recall
Recall (sensitivity) measures the proportion of actual defective parts correctly identified by the model. With 98% accuracy but zero true positives (since the model labels everything as non-defective), recall is 0%, which directly exposes the model's failure to detect any defective parts despite high accuracy.
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.
✗
Accuracy
Why it's wrong here
Accuracy is 98% in this case, which seems good but hides the model's failure to detect any defective parts.
✗
Precision
Why it's wrong here
Precision measures how many predicted defective parts are actually defective. Since no parts are predicted defective, precision is undefined or 0, but recall is a more direct indicator of missing positives.
✓
Recall
Why this is correct
Recall (sensitivity) is the proportion of actual defective parts that the model correctly identifies. A recall of 0% clearly shows the model fails to detect any defects.
Clue confirmation
The clue word "best" in the question point toward this answer.
Related concept
Read the scenario before looking for a memorised answer.
✗
F1 Score
Why it's wrong here
F1 Score is the harmonic mean of precision and recall. It would be 0, but recall directly reveals the issue without combining with precision.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates see 98% accuracy and assume the model is performing well, overlooking that accuracy is inflated by class imbalance and does not measure the model's ability to detect the rare defective class.
Detailed technical explanation
How to think about this question
In imbalanced classification (e.g., 2% defect rate), accuracy is a poor metric because a trivial classifier that always predicts the majority class can achieve high accuracy. Recall focuses on the minority class by calculating TP/(TP+FN); here TP=0 and FN=2% of all parts, so recall=0. Azure Machine Learning's classification evaluation automatically computes per-class metrics, and the confusion matrix would show zero true positives for the defective class, making recall the key diagnostic metric.
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 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. Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option. 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 — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Recall — Recall (sensitivity) measures the proportion of actual defective parts correctly identified by the model. With 98% accuracy but zero true positives (since the model labels everything as non-defective), recall is 0%, which directly exposes the model's failure to detect any defective parts despite high accuracy.
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.
Are there clue words in this question I should notice?
Yes — watch for: "best". Signals that multiple options may be partially correct. Choose the option that most directly solves the exact problem described, not the one that sounds most complete.
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-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.