F-measure (or F-score) is a statistical metric that combines precision and recall into a single score using their harmonic mean. For a given threshold, precision measures the fraction of predicted positives that are truly positive, while recall measures the fraction of actual positives that are correctly identified. The F-measure balances these two metrics: F1 = 2 × (precision × recall) / (precision + recall). Variants Fβ weight recall β² times more than precision. It is used in classification tasks where class imbalance makes accuracy misleading, providing a single number that reflects both false positives and false negatives. [formal: F-measure | substrate: mind | horizon: a moment | explicit: yes | epoch: 0.01]
Accepted ontology entry
f-measure
F-measure (or F-score) is a statistical metric that combines precision and recall into a single score using their harmonic mean. For a given threshold, precision measures the fraction of predicted positives that are truly positive, while r…
Definition
Why it is in scope
A human-made statistical metric that combines precision and recall into a single score using their harmonic mean, used to evaluate the performance of classification models when class balance is uneven. Built to persist through standardization in machine learning evaluation and information retrieval practice.
Names and aliases
- f-measureen · CANONICAL
Relations from this entry
- cmsf7qgxd06p03vv3xyd4mpo0DERIVED_FROM →
F-measure was constructed from precision and recall; recall existed as a metric long before the F1 score combined the two. The component pre-dates and feeds into the composite.
- cms5rqg1s02mmi9iq606htcu1DERIVED_FROM →
F-measure (introduced by Manning and Schutze 1999) was constructed by combining two pre-existing metrics: precision and recall via their harmonic mean. The individual metrics predate and feed into the composite.
- cmrwiv1rn00a8soacg5vdpiogINSTANCE_OF →
F-measure is a specific kind of metric — a quantitative measure of model performance. A competent speaker would call F-measure a metric.
- cms5rqg1s02mmi9iq606htcu1DEPENDS_ON →
The F-measure formula (harmonic mean of precision and recall) literally requires precision to operate. Remove precision from the computation and f-measure cannot be calculated.
- cmsf7qgxd06p03vv3xyd4mpo0DEPENDS_ON →
The F-measure formula (harmonic mean of precision and recall) literally requires recall to operate. Remove recall from the computation and f-measure cannot be calculated.
- cmsfeurc3074l3vv3banqc63wDEPENDS_ON →
f-measure = 2·(precision·recall)/(precision·+·recall), and sensitivity IS recall. Remove sensitivity (recall) and the f-measure formula collapses — it cannot operate without this parameter. Present-tense dependency per Law 8.
Relations to this entry
No accepted relations in this direction.
Record identity
- Created
- Aug 5, 2026, 12:19 AM UTC
- Content hash
- 97502bcd1f7605a3702bcce9e7094087f9b8f8c3054f1e02329f3d1090923730