How to perform oversampling using EM, when target variable is multinomial?

[munitech4u]

I have a dataset which has 1m obs. I have target variable which has 3 categories: 0(90%),1(5%),2(3%),3(2%). I want to oversample the 1,2,3 categories to say 10% each and 0 to 70%. I know, how to oversample for 2 levels, using entperise miner. But how to do it, for multiple categories?

[JasonXin]

Under ASSESS, there is a Decisions Node. If you have a multi-class target, it should be populated there for you to customize the proportions. I am not in front of EM, but recall there is a Custom Editor you can click. Jason Xin