In books I see ROC curves like this:

enter image description here

So I always think the model with the highest AUC is better at any threshold. Is this true in general?

When applying usual classification models, can there be two models for the same classification problem like this, where the first one has a higher AUC, but the second one is better for some applications?

enter image description here


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.