The positive class in a binary classification problem, is usually the class of interest (e.g: fraud, spam, cancer).

Machine learning algorithms try to construct a classifier that can separate these two classes. Here, it does not matter what you call "positive" or "1" or "true"...

Are there examples for problems/algorithms where it is important to define something like a class of interest in supervised learning?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.