Multinomial Logistic Regression in Rapidminer
Hi,
I wanted to perform a Multinomial Logistic Regression for designating our customer types. I do not see any operator for this can you provide some guidance in this regards
Thx
Tagged:
0
Best Answer

Thomas_Ott RapidMiner Certified Analyst, RapidMiner Certified Expert, Member Posts: 1,761 Unicorn
@sunnyal the Generalized Linear Model operator can do Multinominal labels, just have to set the Family parameter to multinominal
2
Answers
Hi @sunnyal,
Is there any difference between polynomial and multinomial logistic regressions? Because if there isn't a difference, I remember that there is an operator named Logistic Regression (Evolutionary), that you can configure to do polynomial regressions.
All the best,
Thank you Rodrigo, Tom,
I also see an operator called Polynomial regression. Would this suffice the need for performing multinomial regression?? Is there a difference between this an Logistic Regression (Evolutionary) and Generalized Linear Model ??
Also, do we have an sample process on Generalized Linear Model with family type as multinomial, that I can infer ??
Thx
@sunnyal The Polynominal Regression operator can only use a numerical label with numerical labels, so you can't use it for a multilabel application. The Logistic Regression (Evolutionary) operator is a lot like a standard LR algo BUT uses a Support Vector Machine to determine the boundary conditions of a binomal label. So that won't work either if you have multilabels (i.e. more than 2).
The best bet, IMHO, is to use the GLM operator. It's a modern implementation and really fast.