The answer is recall, because it directly measures how many actual positive cases the model successfully identifies. In an imbalanced dataset like this one, where only 1% of patients have the rare disease, a model that simply predicts “no disease” for everyone achieves 99% accuracy but a recall of 0%—it finds zero true positives. This is why recall matters more than accuracy for rare events: accuracy can be artificially inflated by the majority class, while recall exposes the model’s failure to detect the critical minority. On the Microsoft Azure AI Fundamentals AI-900 exam, this concept tests your understanding of evaluation metrics for classification, especially when dealing with imbalanced datasets. A common trap is to assume high accuracy means good performance, but the exam expects you to recognize that recall (or sensitivity) is the metric that reveals a model’s inability to catch rare positive cases. Memory tip: “Recall reveals the real rare cases”—if you need to find the needle in the haystack, recall is your metric.
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. The scenario asks you to isolate a root cause — eliminate options that address a different problem before choosing. A key principle to apply: recall measures the proportion of actual positives correctly identified.. 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 model to predict whether a patient has a rare disease (1% prevalence). The model predicts 'no disease' for all patients and achieves 99% accuracy, but fails to identify any actual cases. Which metric would best reveal this failure?
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: Precision would be undefined or 0/0 because the model makes no positive predictions, not directly revealing the failure to catch actual cases.
B
Recall
Recall (sensitivity) would be 0% because the model predicts no positives, making it clear that it misses all actual disease cases.
C
F1 score
Why wrong: F1 score would be 0, but it is the harmonic mean of precision and recall; recall directly conveys the failure to detect positives.
D
Mean absolute error
Why wrong: Mean absolute error is used for regression tasks, not binary classification, so it is inappropriate here.
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 positive cases correctly identified. With 1% disease prevalence and a model that predicts 'no disease' for all patients, recall is 0% because zero true positives are found. Accuracy (99%) is misleading here because the model fails to detect any rare disease cases, and recall directly exposes this failure.
Key principle: Recall measures the proportion of actual positives correctly identified.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
Precision
Why it's wrong here
Precision would be undefined or 0/0 because the model makes no positive predictions, not directly revealing the failure to catch actual cases.
✓
Recall
Why this is correct
Recall (sensitivity) would be 0% because the model predicts no positives, making it clear that it misses all actual disease cases.
Clue confirmation
The clue word "best" in the question point toward this answer.
Related concept
Recall measures the proportion of actual positives correctly identified.
✗
F1 score
Why it's wrong here
F1 score would be 0, but it is the harmonic mean of precision and recall; recall directly conveys the failure to detect positives.
✗
Mean absolute error
Why it's wrong here
Mean absolute error is used for regression tasks, not binary classification, so it is inappropriate here.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates see 99% accuracy and assume the model is performing well, failing to recognize that accuracy is a poor metric for imbalanced datasets and that recall specifically measures the model's ability to catch rare positive cases.
Detailed technical explanation
How to think about this question
Recall is calculated as TP / (TP + FN). In this scenario, true positives (TP) = 0 and false negatives (FN) = all actual disease cases (1% of the population), so recall = 0. This metric is critical in imbalanced classification problems, such as medical diagnosis or fraud detection, where missing a positive case has severe consequences. Under the hood, Azure Machine Learning's classification evaluation module computes recall automatically when you select a binary classification metric, and it is often paired with precision to assess model trade-offs.
KKey Concepts to Remember
Recall measures the proportion of actual positives correctly identified.
Recall is crucial for imbalanced datasets, especially when missing positives is costly.
A model predicting only the negative class will have 0% recall for the positive class.
Recall is calculated as True Positives / (True Positives + False Negatives).
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
Recall measures the proportion of actual positives correctly identified.
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. Recall measures the proportion of actual positives correctly identified. 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.
Review recall measures the proportion of actual positives correctly identified., then practise related AI-900 questions on the same topic to reinforce the concept.
Describe fundamental principles of machine learning on Azure — This question tests Describe fundamental principles of machine learning on Azure — Recall measures the proportion of actual positives correctly identified..
What is the correct answer to this question?
The correct answer is: Recall — Recall (sensitivity) measures the proportion of actual positive cases correctly identified. With 1% disease prevalence and a model that predicts 'no disease' for all patients, recall is 0% because zero true positives are found. Accuracy (99%) is misleading here because the model fails to detect any rare disease cases, and recall directly exposes this failure.
What should I do if I get this AI-900 question wrong?
Review recall measures the proportion of actual positives correctly identified., then practise related AI-900 questions on the same topic to reinforce the concept.
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?
Recall measures the proportion of actual positives correctly identified.
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 →
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 hospital deploys a machine learning model to screen patients for a rare disease. Only 0.1% of patients actually have the disease. The model correctly identifies most positive cases but also flags many healthy patients as potentially having the disease. The hospital wants to minimize the number of healthy patients who are incorrectly told they might have the disease. Which metric should the model optimize?
medium
A.Recall
✓ B.Precision
C.F1 score
D.Accuracy
Why B: Precision measures the proportion of positive identifications that are actually correct. In this scenario, the hospital wants to minimize false positives (healthy patients incorrectly told they might have the disease). Optimizing precision directly reduces false positives, which is the stated goal.
Last reviewed: Jun 11, 2026
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.
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.