When evaluating a [[Machine Learning|machine learning]] [[Classification|classification]] model, **precision** is the [[Error Metrics|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. $ \textrm{Precision} = \frac{\textrm{TP}}{\textrm{TP} + \textrm{FP}} $ It is very tightly coupled with another [[Error Metrics|error metric]], [[Recall|recall]]. Real life models usually require by their very nature a higher precision than recall or the other way around.