Which metric avoids false negatives, calculated as correct positive predictions divided by total actual positives?

Which metric avoids false negatives, calculated as correct positive predictions divided by total actual positives?

• A. Recall
• B. Accuracy
• C. Precision
• D. F-score

Answer: (A)

Recall focuses on how well you identify actual positives. It is calculated as true positives divided by the sum of true positives and false negatives. This metric directly penalizes missed positives, so higher recall means fewer false negatives. In contexts where missing a positive is costly, recall is the preferred measure. Precision, on the other hand, cares about how many of the predicted positives are correct, not about catching all positives. Accuracy mixes positives and negatives and can hide poor performance on the positive class. The F-score combines precision and recall, but the described calculation matches recall specifically. So, the best answer is recall.

Recall focuses on how well you identify actual positives. It is calculated as true positives divided by the sum of true positives and false negatives. This metric directly penalizes missed positives, so higher recall means fewer false negatives. In contexts where missing a positive is costly, recall is the preferred measure. Precision, on the other hand, cares about how many of the predicted positives are correct, not about catching all positives. Accuracy mixes positives and negatives and can hide poor performance on the positive class. The F-score combines precision and recall, but the described calculation matches recall specifically. So, the best answer is recall.