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

• A. Precision
• B. Recall
• C. F-score
• D. Confusion matrix

Answer: (A)

Precision measures how reliable the positive predictions are. It is the proportion of true positives among all instances the model labeled as positive, calculated as true positives divided by the total number of predicted positives. Because FP (false positives) increase the denominator, more false positives lower precision; fewer false positives raise precision. For example, if 25 of 30 predicted positives are correct, precision is 25/30 ≈ 0.83, indicating most of the positives the model claimed are indeed positive.

Recall, by contrast, looks at how many actual positives were found, regardless of how many negatives were mislabeled as positive, and F-score blends precision and recall. A confusion matrix is a table that shows true positives, false positives, true negatives, and false negatives, not a single ratio.