Using a classifier trained in the classification learner app, how to use it at a different point in the ROC curve, and how are the ROC points calculated?

Hello. When using the classification learner app you can choose and train a model type. The app then selects a point in the ROC curve by itself. I have an application where the true positive rate must be 1, so I want to have the model parameters different then ones that are produced by the standard "hit train" method of classification learner. I am also wondering how the app makes the ROC curves, since this shows that it is possible to set the model at a different point in the ROC curve. A variation of this was also asked in 2017 here but no answer was given.

Answer 1

[Alex van der Meer]

I solved the issue and succesfully finished my project :) Look at my and benjamins answer to a similar question here https://nl.mathworks.com/matlabcentral/answers/346479-how-does-the-classification-learner-app-generate-roc-curves-for-decision-trees-and-how-do-i-tune-the