Glossary term
Glossary term
Evaluation and Benchmarks
A "roll-up" binary classification metric that relies on both precision and recall. Here is the formula:
Click the icon to see examples.
Created for this library
A fraud team reports F1 alongside precision and recall to give business owners a single quality number when classes are imbalanced.
A medical screening team reports F1 on rare-disease detection because both false positives and false negatives carry real cost.
A search relevance team tracks F1 on its query intent classifier as a release readiness check before promoting any new model.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License