Glossary term
Glossary term
Foundations
An example in which the model correctly predicts the negative class. For example, the model infers that a particular email message is not spam, and that email message really is not spam.
Created for this library
A fraud team monitors true negatives in its production logs to confirm the model is not declining legitimate transactions excessively.
A medical screening team reports true negatives so clinicians see how often healthy patients are correctly cleared.
An email security team monitors true negatives to confirm legitimate mail is reliably delivered.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License