AAISM · Question #144
Which of the following is BEST for analyzing true positives, true negatives, false positives, and false negatives produced by an AI model?
The correct answer is C. Confusion matrix. A confusion matrix is a purpose-built table that displays the four classification outcomes - true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN) - in a structured grid, providing a complete picture of a classifier's performance. Precision (B)
Question
Which of the following is BEST for analyzing true positives, true negatives, false positives, and false negatives produced by an AI model?
Options
- AHyperparameter tuning
- BPrecision
- CConfusion matrix
- DRecall
How the community answered
(33 responses)- A3% (1)
- B3% (1)
- C94% (31)
Explanation
A confusion matrix is a purpose-built table that displays the four classification outcomes - true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN) - in a structured grid, providing a complete picture of a classifier's performance. Precision (B) and recall (D) are single metrics derived from the confusion matrix but do not show all four values simultaneously. Hyperparameter tuning (A) is a model optimization technique, not an evaluation tool. The confusion matrix is the foundational artifact for understanding classification errors and is the only option that directly represents all four outcome categories.
Topics
Community Discussion
No community discussion yet for this question.