引導式測驗 · 中等 等級
分類閾值調校測驗
測試閾值權衡、驗證集選擇、精確召回分析以及傳統 0.5 截止值背後的條件。
問題 1 的 8
對於已校準的後驗機率,且正確決策的成本為零時,何時 0.5 的截斷點是貝氏決策規則(Bayes decision rule)?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 對於已校準的後驗機率,且正確決策的成本為零時,何時 0.5 的截斷點是貝氏決策規則(Bayes decision rule)?
- Only when the dataset contains equal numbers of each class
- When false-positive and false-negative costs are equal, regardless of class balance
- Whenever the model has over 90% accuracy
- When false negatives cost more than false positives
- 為什麼醫院分流的例子將閾值從 0.5 降低到 0.2?
- To reduce the number of alerts sent to staff
- Because the model's accuracy improved at 0.2
- Because 0.2 is the industry-standard default
- To accept more false alarms in exchange for catching more true emergencies
- 根據指南所述,Youden's J 統計量最大化了什麼?
- Sensitivity plus specificity minus one
- Precision alone
- The raw accuracy of the model
- The number of true negatives only
- 根據指南,調整閾值會改變底層訓練好的模型嗎?
- Yes, it retrains the model's weights
- Yes, but only for tree-based models
- No, it only changes where the decision line is drawn on the same probability outputs
- No, but it deletes the model's training data
- 根據技術章節,應該在什麼類型的資料集上進行閾值選擇?
- The same training data used to fit the model
- A held-out validation set
- Randomly generated synthetic data
- The final test set reserved for reporting results
- Why did the fraud detection example raise its threshold above 0.5 during a high-volume shopping period?
- To eliminate the need for human reviewers entirely
- Because fraud rates always drop during holidays
- Because raising the threshold improves the model's training accuracy
- To avoid overwhelming human reviewers with false positives, accepting slightly more missed fraud
- When the class mix or error costs change after deployment, what should the team do with its operating cutoff?
- The model architecture must be replaced
- Nothing, since thresholds are fixed once set
- Revalidate whether the threshold still meets the new operating goals
- The training data must be deleted
- What tool did the marketing team use instead of accuracy to select a threshold for a rare target segment?
- Precision-recall curves
- 隨機數產生器
- The model's training loss curve
- A fixed 0.9 threshold by default