Question 359 of 985
AI-900 Practice Question: Describe fundamental principles of machine learning on Azure
A data scientist has trained a binary classification model to detect fraudulent credit card transactions. The dataset contains 99.9% legitimate transactions and only 0.1% fraudulent ones. The model predicts all transactions as legitimate, achieving 99.9% accuracy on the test set. However, the business requires the model to actually catch as many fraudulent transactions as possible. Which metric would best reveal the model's failure to identify fraud?
⚠ Common exam trap
The trap here is that candidates see the high accuracy (99.9%) and assume the model is performing well, failing to recognize that accuracy is meaningless in extreme class imbalance and that recall is the metric designed to evaluate the model's ability to find the rare positive class.
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
✓
Recall
Recall (also known as sensitivity) measures the proportion of actual positive cases (fraudulent transactions) that were correctly identified by the model. In this scenario, the model predicts all transactions as legitimate, so it correctly identifies 0 out of the 0.1% fraudulent transactions, yielding a recall of 0%. This directly reveals the model's complete failure to catch fraud, despite the high accuracy.
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 the ratio of all correct predictions to total instances. Because fraudulent transactions are extremely rare, a model that blindly predicts 'legitimate' for every case can post 99.9% accuracy while catching none of the fraud. This metric is dominated by the large negative class, so it cannot reveal the complete failure to identify the minority positive class.
- ✓
Recall
Why this is correct
Recall measures sensitivity to the positive class: true positives divided by the sum of true positives and false negatives. Since the model never produces a fraud prediction, true positives is zero while false negatives equals all actual fraud, making recall exactly 0%. This directly exposes the model's inability to catch fraud, which is the critical requirement in fraud detection.
- ✗
Precision
Why it's wrong here
Precision is the fraction of predicted positive cases that are truly positive. Because the model makes no positive predictions, precision is undefined or 0, but it does not directly indicate the missed fraud cases as clearly as recall.
- ✗
F1 score
Why it's wrong here
F1 score is the harmonic mean of precision and recall and would collapse to zero if recall is zero, matching the failure signal. However, it is a composite metric that also incorporates precision, which is pathological when no positives are predicted. As a blended score, it is less immediately diagnostic than recall for answering, 'what fraction of actual fraud did we catch?'
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 →
Last reviewed: Jun 11, 2026
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.