F1 score
Also: F1, F-score, F-measure, F1-score
A single number combining precision P and recall R as 2PR / (P + R). Because it is a harmonic mean, a very low value of either one drags F1 down, which makes it a common metric for imbalanced classification.
F1 = 2 · P · R / (P + R)
Example
With precision 0.8 and recall 0.67, F1 = 2 · 0.8 · 0.67 / (0.8 + 0.67) ≈ 0.73; but precision 1.0 with recall 0.1 gives F1 ≈ 0.18, not the 0.55 an average would suggest.