Options

[SOLVED] Output of Class Probability according to the Modell

RLorrigRLorrig Member Posts: 4 Contributor I
edited November 2018 in Help
Hi all,

I'm actually experimenting with classification on the German Data Set (CreditScoring), and was wondering if there is a possibility to get an output of the class probablities assigned to the Data by the classificator. I'm mainly working with the decision tree operator as it is easy to understand.
I also tried several other classificators but wasn't able to find something like this.

I hope this question isn't too stupid, because I'm relativly new to Data Mining and quite unsure about some of the things I'm acctually trying.

Edit: I think one of the confidence attributes added by the apply model operator might be what i'm looking for, but apparently I can't find any documantation for it. Also, if this is what I'm looking for, I'm not sure how to tell the decision tree operator where to set the cut-off, as it says the confidence parameter is only used for prepruning.

Edit2: I think i might have found what i was looking for. If I'm coorect, a can use the find and apply threshold operators. Am I correct thinking that the find threshold operator can also apply a costmatrix instead of the metacost operator?

Edit3: Ok, I'm done... I should have mentioned that i was working with ROC curves. What i was looking for was actually the create/apply threshold operators. Nonetheless, please tell me if I'm wrong in what I'm doing :)

Thanks in Advance
Sign In or Register to comment.