F1 score

The harmonic mean of precision and recall, a single number summarizing both at once.

The F1 score is the harmonic mean of precision and recall, $F_1 = 2\cdot\dfrac{\text{Precision}\cdot\text{Recall}}{\text{Precision}+\text{Recall}}$ , summarizing both into one number that penalizes a model for being weak on either one, unlike a plain average which can stay high even when one of the two is poor.

Examples

The spam filter above (precision $0.9$ , recall $0.6$ ) has $F_1=2(0.9)(0.6)/(0.9+0.6)\approx0.72$ , penalized more than a plain average would be for its weaker recall.