True Negative (TN)

What is a True Negative (TN)?

When evaluating the prediction of a model given a sample, a True Negative (TN) is the outcome where the model correctly predicts the negative class.

Consider the example of a model which classifies emails as either spam (positive class) or not spam (negative class). If the actual label of the sample is not spam and the model correctly predicts not spam then this outcome will be considered a True Negative.