Precision Recall Calculator
Two Different Questions About the Same Prediction
Precision answers "of everything the model flagged as positive, how much was actually positive?" Recall answers a different question: "of everything that was actually positive, how much did the model catch?" A classifier can score high on one while scoring poorly on the other, which is why both numbers need to be reported together rather than picking just one.
The Formula
Precision = TP / (TP + FP) × 100
Recall = TP / (TP + FN) × 100
Recall = TP / (TP + FN) × 100
Where This Matters
- Spam filtering — high precision matters most, since flagging a legitimate email as spam (a false positive) is costly.
- Disease screening — high recall matters most, since missing an actual case (a false negative) can be far worse than a false alarm.
- Search relevance — balancing precision (returned results are relevant) against recall (all relevant results are returned).
Worked Example
| Metric | Calculation | Result |
|---|---|---|
| Precision | 80 / (80 + 20) | 80.00% |
| Recall | 80 / (80 + 10) | 88.89% |
Precision = TP/(TP+FP) x 100; Recall = TP/(TP+FN) x 100.
How to Use This Calculator
- Enter True Positives (TP).
- Enter False Positives (FP).
- Enter False Negatives (FN).
- Select Calculate to get precision and recall as percentages.
Related Calculations
Combine both numbers into one score with the F1 Score Calculator, or see the full picture including true negatives with the Confusion Matrix Calculator.