1.3Standard
A fraud detector must catch most fraud.
False alarms also create investigation cost.
Choose two practices.
× Incorrect
Set recall and precision targets from the cost of missed fraud and false alarms, then evaluate a threshold on representative data and monitor changes.
Detailed explanation
CorrectMeasure precision and false-positive cost for the chosen threshold
Too many alarms can consume investigation capacity.
IncorrectChoose a threshold from one convenient example
The operating point needs representative data.
CorrectSet a recall target when missing a true fraud case is especially costly
Recall measures how many actual positive cases are found.
IncorrectMaximize accuracy without considering class imbalance
A majority class can hide missed fraud.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 1.3の評価指標、分類、ビジネス要件を確認する。
Official references
What to confirm
正解率だけでなく業務コストを含む指標選択を説明できる。
Key points
- Recall
- Precision
- Threshold
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Compare the definition with the AIF-C01 objective and the service documentation before applying it.
- Keep the concept separate from a particular answer choice or implementation step.
Foundation review
Recall
The proportion of actual positive cases that the model identifies.
Precision
The proportion of predicted positive cases that are actually positive.
Question IDAWS-AIF-294
EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
Last technical review2026-08-20
Report an error or rights issue