How many Troubleshooting Scenario Questions questions are on this page?

This page has 8 Troubleshooting Scenario Questions scenario questions for the AI-900 exam, each with detailed explanations and wrong-answer analysis.

How should I approach AI-900 scenario questions?

Read the full scenario before looking at the answer options. Identify the constraint or requirement in the scenario, then eliminate options that are generally true but wrong for this specific case. Scenario questions reward careful reading over pattern matching.

← Back to Microsoft Azure AI Fundamentals AI-900 questions

Scenario-based practice

Troubleshooting Scenario Questions

Practise Microsoft Azure AI Fundamentals AI-900 practice questions — original exam-style scenarios covering every exam domain, with detailed explanations, wrong-answer analysis, and common exam traps.

Start full practice test Read exam guide

scenario questions

AI-900

exam code

Microsoft

vendor

Scenario guide

How to approach troubleshooting scenario questions

These questions describe a network symptom and ask you to identify the root cause or the correct fix. They appear across all certification exams and reward systematic thinking over memorisation. The best candidates follow a consistent troubleshooting framework even under time pressure.

Quick answer

Troubleshooting Scenario Questions questions test whether you can apply the concept in context, not just recognise a definition.

How the topic appears in realistic exam-style scenarios.

Which detail in the question changes the correct answer.

How to eliminate plausible but wrong options.

How to connect the question back to the wider exam objective.

Practice scenarios

Question 1mediummultiple choice

Full question →

A self-driving car company develops an AI system that is highly accurate in testing but fails to consistently detect pedestrians during heavy rain. Which Microsoft responsible AI principle is most directly violated?

A
Fairness
Why wrong: Fairness relates to ensuring AI systems do not discriminate against groups, which is not the primary issue here.
B
Reliability and safety
This principle ensures AI systems operate safely and consistently; failing in adverse weather violates that.
C
Privacy and security
Why wrong: Privacy and security involve protecting data, not the consistency of system performance.
D
Transparency
Why wrong: Transparency is about understanding how decisions are made, not about system robustness.

Full breakdown with real-world context →

Question 2hardmultiple choice

Full question →

A data scientist is training a binary classification model to detect fraudulent transactions. The dataset contains only 1% fraudulent transactions. The model achieves 99% accuracy on the test set, but when deployed, it fails to detect most actual fraud cases. Which metric would best reveal this issue?

A
Accuracy
Why wrong: Accuracy is misleading in imbalanced datasets because a model that never predicts fraud can still show high accuracy.
B
Precision
Why wrong: Precision measures how many of the predicted fraud cases are actually correct, but it doesn't show how many real fraud cases were missed.
C
Recall
Recall measures the fraction of actual fraud cases that the model correctly identifies. A low recall reveals the model's failure to detect fraud.
D
F1 score
Why wrong: F1 score combines precision and recall; while it gives a balanced view, recall alone is the most direct metric to expose the model's inability to catch fraud cases.

Full breakdown with real-world context →

Question 3mediummultiple choice

Full question →

A company builds an AI system to filter job applications and rank candidates. The system is trained on historical hiring data. To reduce potential bias, the company removes protected attributes such as gender and ethnicity from the training data. However, after deployment, the system still shows a statistically significant bias against female candidates. Which Microsoft responsible AI principle most directly requires the company to investigate and address this remaining bias, even when protected attributes are removed?

A
Fairness
Fairness requires AI systems to treat all groups equitably and address any sources of bias, including proxy variables that correlate with protected attributes.
B
Inclusiveness
Why wrong: Inclusiveness is about designing systems that are accessible and usable by people of all abilities, not specifically about addressing bias in hiring.
C
Reliability and safety
Why wrong: Reliability and safety focus on ensuring the system works correctly and does not cause harm; it does not directly address bias or fairness.
D
Transparency
Why wrong: Transparency involves making the system's behavior understandable to users, but it does not specifically require addressing biased outcomes.

Full breakdown with real-world context →

Question 4hardmultiple choice

Full question →

A data scientist is building a classification model to detect fraudulent transactions. The dataset has 1,000,000 legitimate transactions and only 1,000 fraudulent ones. The model achieves 99.9% accuracy on the test set, but it fails to catch most fraudulent cases. Which metric should the data scientist prioritize to better evaluate the model's performance on this imbalanced dataset?

A
Accuracy
Why wrong: Accuracy is not informative for imbalanced datasets because it can be high even if the model fails to detect any fraudulent transactions.
B
Mean Squared Error
Why wrong: Mean Squared Error is a metric for regression tasks, not for classification evaluation.
C
Recall
Recall measures the proportion of actual fraudulent transactions that the model correctly identifies, which is the key metric for catching fraud.
D
R-squared
Why wrong: R-squared is a regression metric that indicates the proportion of variance explained; it is not suitable for classification evaluation.

Full breakdown with real-world context →

Question 5easymultiple choice

Full question →

An autonomous delivery robot uses AI to navigate sidewalks. The robot occasionally fails to detect pedestrians in low-light conditions, leading to near-collisions. The company wants to ensure the system is robust and safe before wider deployment. Which Microsoft responsible AI principle is most directly relevant?

A
Fairness
Why wrong: Fairness addresses biases in AI that could lead to discrimination, but the primary concern here is physical safety, not differential treatment of individuals.
B
Privacy and security
Why wrong: Privacy and security focus on protecting data and preventing unauthorized access. While important, the core issue is the robot's inability to detect pedestrians safely, not data handling.
C
Reliability and safety
Reliability and safety ensure AI systems perform as intended and do not cause harm. The robot's detection failures in low light present a safety risk that must be mitigated.
D
Transparency
Why wrong: Transparency means explaining AI decisions, but the immediate need is to make the system safe, not to explain its failures to pedestrians.

Full breakdown with real-world context →

Question 6mediummultiple choice

Full question →

An autonomous drone delivery company uses an AI model to navigate. During testing in a new city, the model fails to detect power lines and crashes into them. The company wants to ensure their system is robust to unusual conditions. Which Microsoft responsible AI principle is most directly relevant?

A
Fairness
Why wrong: Fairness focuses on treating all people equitably and avoiding bias, not on system robustness or safety.
B
Privacy and Security
Why wrong: Privacy and Security deals with data protection and securing the system against unauthorized access, not physical safety during operation.
C
Reliability and Safety
This principle ensures AI systems perform as expected without causing harm, especially in unforeseen circumstances.
D
Inclusiveness
Why wrong: Inclusiveness aims to design AI that serves the widest range of users, not specifically system robustness or safety.

Full breakdown with real-world context →

Question 7mediummultiple choice

Read the full NAT/PAT explanation →

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?

A
Precision
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.

Full breakdown with real-world context →

Question 8hardmultiple choice

Full question →

A data scientist trains a binary classification model to detect fraudulent transactions. The dataset contains only 2% fraudulent transactions. The model achieves 98% overall accuracy, but it fails to detect any fraudulent transactions, classifying all transactions as legitimate. Which metric would most clearly reveal this failure?

A
Precision
Why wrong: Precision would be low or undefined because the model predicts no positive cases, but recall more directly shows the inability to find fraud.
B
Recall
Recall (true positive rate) is 0 when no fraudulent transactions are identified, exposing the model's failure.
C
F1 score
Why wrong: F1 score is the harmonic mean of precision and recall; it would be 0 but does not pinpoint the issue as clearly as recall alone.
D
Specificity
Why wrong: Specificity measures true negative rate, which would be high (98%) and thus hide the failure to detect fraud.

Full breakdown with real-world context →

These AI-900 practice questions are part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style AI-900 questions with detailed explanations, topic-based practice, mock exams, readiness tracking, and study analytics.

Troubleshooting Scenario Questions

How to approach troubleshooting scenario questions

Quick answer

Related AI-900 topic practice pages

Describe Artificial Intelligence workloads and considerations practice questions

Describe fundamental principles of machine learning on Azure practice questions

Describe features of computer vision workloads on Azure practice questions

Describe features of Natural Language Processing workloads on Azure practice questions

Describe features of generative AI workloads on Azure practice questions

AI-900 fundamentals practice questions

AI-900 scenario practice questions

AI-900 troubleshooting practice questions

Practice scenarios

A self-driving car company develops an AI system that is highly accurate in testing but fails to consistently detect pedestrians during heavy rain. Which Microsoft responsible AI principle is most directly violated?

An autonomous drone delivery company uses an AI model to navigate. During testing in a new city, the model fails to detect power lines and crashes into them. The company wants to ensure their system is robust to unusual conditions. Which Microsoft responsible AI principle is most directly relevant?

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?