Glossary term
Glossary term
Evaluation and Benchmarks
The proportion of actual positive examples for which the model mistakenly predicted the negative class. The following formula calculates the false negative rate:
See Thresholds and the confusion matrix in Machine Learning Crash Course for more information.
Created for this library
A medical screening team sets a maximum false negative rate of 5 percent on its early-stage cancer classifier before clinical sign-off.
A cybersecurity team requires false negative rate below 2 percent on known-threat detection before promoting a new model.
A fraud team monitors false negative rate weekly to confirm the model is not letting more high-value fraud through after a threshold change.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License