Hi I want to doing feature selection with rapidminer with forward selection and backward elimination. there are three operator: 1:optimize selection(forward and backward), 2: optimize weight forward and backward and 3: forward selection and backward elimination operators. all there operator needs to have a inner operator like cross-validation operator toe evaluate the model. But in output of these three operator there are different selected feature and different accuracy. also when i do a cross validation separately with selected attributes by select attribute operator without using the forward and backward operator and with only use the their selected attributes, there are different results. i dont know whats wrong here! anyone can help? thanks
