I'm working on a project and want to use decisions tree (because I have both catgorical and numerical values in my input and don't want to transform the categoricals variables) to predict an output varaible , but the problem is that I don't have only one output variable but 4 !


that picture is a look for my output dataset:

  • The first one will can be predict with a regression decision tree .

  • the the rest if can be predict with a classification decision tree but with more than 2 classes so a multi-class.

    So I want to know what is the best solution to approach this problem:

  • Using 4 differents decisions trees one tree for each variables ?

  • Or using 1 multi-output decision tree?

  • What are the avantages and inconvenients of each approach?


1 Answer 1


I check and found this in scikit-learn documentation and I'm sure that is the answer I was looking for!

Multioutput classification support can be added to any classifier with MultiOutputClassifier. This strategy consists of fitting one classifier per target. This allows multiple target variable classifications. The purpose of this class is to extend estimators to be able to estimate a series of target functions (f1,f2,f3...,fn) that are trained on a single X predictor matrix to predict a series of reponses (y1,y2,y3...,yn).


Your Answer

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

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