Quiz collegato alla guida · Medio Livello
Classification Threshold Tuning Quiz
Tests threshold tradeoffs, validation-set selection, precision-recall analysis, and the conditions behind the conventional 0.5 cutoff.
Domanda 1 di 8
Per probabilità a posteriori calibrate con costi pari a zero per decisioni corrette, quando un limite di 0,5 è la regola decisionale di Bayes?
Anteprima di ogni domanda8 domande
Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.
- Per probabilità a posteriori calibrate con costi pari a zero per decisioni corrette, quando un limite di 0,5 è la regola decisionale di Bayes?
- 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
- Perché l’esempio del triage ospedaliero ha abbassato la soglia da 0,5 a 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
- Cosa massimizza la statistica J di Youden, come descritto nella guida?
- Sensitivity plus specificity minus one
- Precision alone
- The raw accuracy of the model
- The number of true negatives only
- Secondo la guida, l'ottimizzazione della soglia modifica il modello addestrato sottostante?
- 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
- Su quale tipo di set di dati deve essere eseguita la selezione della soglia, secondo la sezione tecnica?
- 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
- Un generatore di numeri casuali
- The model's training loss curve
- A fixed 0.9 threshold by default