AI-102 Question 145
Single answerYou are evaluating the performance of a custom vision model that classifies defective and non-defective products in a manufacturing pipeline. The model's precision is calculated as 0.92, recall as 0.70, and accuracy as 0.85. Which metric should you prioritize if minimizing false positives is critical to avoid incorrectly rejecting non-defective products?
- A
Precision
- B
Recall
- C
Accuracy
- D
F1 Score
Show answer and explanation
Correct answer: A
Explanation
When minimizing false positives is critical, precision is the most relevant metric as it measures the proportion of true positive predictions among all positive predictions. This ensures the model is highly selective when identifying defective products, reducing the likelihood of incorrectly rejecting non-defective ones.
- A. Correct.
Precision is the proportion of correctly identified positive samples (defective products) out of all predicted positives. High precision ensures fewer false positives, which is critical for minimizing incorrectly rejecting non-defective products.
- B. Incorrect.
Recall is the proportion of correctly identified positive samples out of all actual positive samples. While recall is important, it focuses on minimizing false negatives rather than false positives, which is not the priority in this scenario.
- C. Incorrect.
Accuracy measures overall correctness but does not focus specifically on false positives or false negatives. It is not the best metric for this scenario as it may be skewed by an imbalanced dataset.
- D. Incorrect.
F1 Score is the harmonic mean of precision and recall. While it balances the two metrics, it is not solely focused on minimizing false positives, which is the priority in this case.