Properties2
| Type | Concept |
| Note created | Feb 17, 2025 |
When evaluating a machine learning classification model, precision is the error metric based on the fraction of relevant instances among the retrieved instances. In the context of binary classification, could be understood as the portion of predicted positives that are indeed positives.
It is very tightly coupled with another error metric, recall. Real life models usually require by their very nature a higher precision than recall or the other way around.