Define Success Criteria for Test CERTIFIED-DATA-SCIENCE-PRACTITIONER Practice Questions (Page 5)

Questions 21–23

1. 21application · medium

   A healthcare startup is developing a model to screen for a rare disease. The cost of missing a case (false negative) is extremely high, but the cost of a false positive is relatively low (just additional testing). The team needs to set a threshold for the model's predicted probability. Which threshold strategy best aligns with the business objective?

   • ASet a high threshold (e.g., 0.9) to ensure high precision
   • BSet the threshold based on the highest F1-score
   • CSet a low threshold (e.g., 0.3) to increase recall
   • DSet the threshold at 0.5 to balance precision and recall
   Reveal Solution Discussion Select an answer first
2. 22foundation · medium

   A dataset has a highly imbalanced class distribution, with only 2% of samples belonging to the positive class. Which metric is more informative than accuracy for evaluating a classification model?

   • AR-squared
   • BF1-score
   • CAccuracy
   • DMean squared error (MSE)
   Reveal Solution Discussion Select an answer first
3. 23application · medium

   A team is developing a spam detection model. The business has specified that the model should have a precision of at least 0.95 to avoid blocking important emails. During testing, the model achieves a precision of 0.92. What should the team do to meet the success criterion?

   • AAccept the current precision as sufficient
   • BChange the success criterion to recall ≥ 0.95
   • CLower the threshold to increase precision
   • DRaise the threshold to increase precision
   Reveal Solution Discussion Select an answer first