~ F-score

In statistical classification, the F-score is a measure of accuracy, based on the precision and accuracy of a classifier. It is defined by the positive real factor $\beta$, as

$$ F_\beta(x) = (1 + \beta^2) \cdot \frac{\text{precision}(x) \cdot \text{recall}(x)}{\left(\beta^2 \cdot \text{precision}(x)\right) + \text{recall}(x)}, $$

where $x$ is the class being classified.

Typically, we consider the F1-score, which is the harmonic mean between the precision and accuracy, namely

$$ F_1(x) = 2\frac{\text{precision}(x)\cdot\text{recall}(x)}{\text{precision}(x) + \text{recall}(x)}. $$

Page made with mdzk