Using Boruta and Scaling with neural network

Question

When using Boruta for variable selection and also scaling your complete data set to values between 0 and 1 is it typical to select variables using Boruta based on the scaled values or the raw values?

Answer 1

Boruta is based on random forest, which is an ensemble of decision trees. Decision trees do not need to be scaled, because selecting a split on one scale is equivalent to selecting a re-scaled split on an alternative scale.

See also:

Scaling/Normalization not need for tree based models