Calculadora de Precisão (classificação)
- Created by
- Renato Passos, Eng. de Software
- Reviewed by
- Renato Passos, Eng. de Software
Last updated: Apr 18, 2026
Formula
Precision = TP / (TP + FP)
About this calculator
The Precision Calculator is a statistical tool designed to compute the precision of a classification model. Precision measures the proportion of true positives (TP) relative to the total number of cases classified as positive, i.e., TP divided by the sum of TP and false positives (FP). This metric is essential for evaluating models where false positives are costly, such as in medical diagnoses or fraud detection.
The operation is simple: you enter the values of true positives and false positives, and the calculator applies the formula Precision = TP / (TP + FP). The result is a number between 0 and 1 (or 0% to 100%), indicating the reliability of positive classifications. High values mean the model rarely misclassifies a negative case as positive.
Use this calculator when evaluating binary classification systems, such as in disease diagnosis, spam filters, or credit scoring models. Precision is especially useful when the cost of a false positive is high. For example, in a test for a serious disease, a false positive can cause unnecessary stress and additional costs.
Caution: precision should not be used in isolation, as it ignores false negatives. For a complete evaluation, combine it with other metrics like recall and F1-score. Also, ensure that the input data (TP and FP) are correct and adequately represent the model's performance.
Frequently asked questions
What does a precision of 0.9 mean?
It means that 90% of the positive classifications made by the model are correct, i.e., out of every 100 times the model predicted positive, 90 were actually positive.
Can I use precision alone to evaluate my model?
No, it is recommended to combine it with other metrics like recall and F1-score, as precision ignores false negatives and may provide an incomplete view of performance.
What is the difference between precision and accuracy?
Precision measures the correctness of positive predictions (TP/(TP+FP)), while accuracy measures overall correctness (TP+TN)/(TP+TN+FP+FN). Precision focuses on predicted positives, accuracy on all classes.
What if my number of false positives is zero?
If FP = 0, the precision will be 1 (100%), meaning all positive predictions were correct. This is ideal but may occur in small datasets or very specific models.
Does this calculator work for multiclass classification?
It is designed for binary classification. For multiclass, you can compute precision per class (one-vs-rest) or use averages like macro or weighted.