F score

Terms from Artificial Intelligence: humans at the heart of algorithms

The glossary is being gradually proof checked, but currently has many typos and misspellings.

The F score is an accuracy metric that combines precision and recall. It is defined as the harmonic mean of precision and recall, that is:
1/F = 0.5*( 1/precision + 1/recall )

There are variants (e.g. Fβ that weight precision and recall differently. Also not to be confused with the F distribution used in statistical testing.

Used in Chap. 9: pages 120, 129