AWS Certified AI Practitioner (AIF-C01) Practice Questions

AWS Certified AI Practitioner (AIF-C01) exam preparation

AWS Certified AI Practitioner (AIF-C01) practice questions in English: 180 questions with explanations. The mock exam has 65 questions and 90 minutes.

AWS Certified AI Practitioner (AIF-C01) free question 2 / 10 · Domain 1: Fundamentals of AI and ML

A team is evaluating a model for a medical test. Above all, they want to avoid missing people who are positive by classifying them as negative. According to the SageMaker Autopilot metrics page, which metric should they weigh most heavily?

  1. Precision (positive predictive value)
  2. Accuracy (overall correct rate)
  3. Recall (sensitivity, true positive rate)
  4. Root mean square error (RMSE)
Show the answer and explanation

Answer: C

Why this is correct
The metrics page defines recall as the fraction of actual positives that were correctly predicted as positive, and says that in cancer screening recall matters because it is important to detect all true positives. It is the metric for cases where you want fewer false negatives (actual positives predicted as negative), that is, to avoid missed cases. The page also cautions that recall alone is not enough, because predicting everything as positive gives a perfect recall.

Why the other options are wrong
"Precision (positive predictive value)" … Precision is the fraction of predicted positives that are really positive. The page says it matters when a false positive is costly, such as a safety system for an airplane wrongly judged safe. That points the opposite way from avoiding missed cases (false negatives).
"Accuracy (overall correct rate)" … Accuracy is the share of predicted classes that match the actual ones. With few positives, it can look high even when many cases are missed, so it does not directly measure the goal of avoiding misses. The page says BalancedAccuracy is the better measure for imbalanced data.
"Root mean square error (RMSE)" … RMSE is the square root of the mean of squared differences between predicted and actual values, an error metric for regression (numeric prediction). It does not measure missed cases in a positive-or-negative classification.

Key point
The F1 score is the harmonic mean of precision and recall, used when you want to balance the two. Exam Guide objective 1.3.6 asks you to explain model performance metrics separately from business metrics such as cost per user and ROI.

Go to the AWS Certified AI Practitioner (AIF-C01) practice app (10 free questions; purchase unlocks all questions)

See the full practice set