Noob question..

Accuracy is defined as percentage of predictions that are correct.

Accuracy = (True Positives + True Negatives)/(All classifications)

Precision is defined as percentage of positive predictions that are correct.

Precision = (True Positives)/(True Positives + False Positives)

Is there a term for the percentage of negative predictions that are correct:

UnPrecision = (True Negatives)/(True Negatives+ False Negatives) ?

Similarly, how about:

UnRecall = (True Negatives)/(True Negatives + False Positives) ?

If not, why not?

Or is it just a case of semantics, where we just swap the terms positive and negative if needed, so we can use the same forumla?


2 Answers 2


You seem to be looking for the Negative Predictive Value and the True Negative Rate.


Your "UnRecall" is usually called "specificity" and my suggested name for "UnPrecision" is "exclusion" but I don't know if that is a standard. The other piece is "sensitivity" which is TP/(TP+FN).


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.