False negatives are costly in an approval model.
Map scores to business decisions.
Choose two practices.
Choose a classification threshold from validation precision, recall, group impact, and business costs rather than a fixed convention.
Detailed explanation
Scores are mapped to business needs.
Scores are mapped to business needs.
Bias is less likely to be missed.
Bias is less likely to be missed.
Costs and distributions differ.
Costs and distributions differ.
Precision and recall change.
Precision and recall change.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 1.2の分類しきい値、適合率、再現率、公平性を確認する。Expected result
誤りのコストとグループ影響を考慮してしきい値を設定できる。Key points
- Threshold
- Business cost
- Group gap
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
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.