thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Foundational

F1 Score

The harmonic mean of precision and recall: 2PR / (P + R).

Definition

F1 balances precision and recall in a single number and is low if either is low. It is a standard metric for imbalanced classification and for extraction tasks such as named entity recognition. The F-beta score weights recall beta times as much as precision.

Example

Precision 0.8 and recall 0.6 give F1 of about 0.686.

Exam tip

Choose F1 when both false positives and false negatives matter and classes are imbalanced.

Related terms