Binomial GLM Feature Selection with rfe function in caret

Question

Is it possible to use the rfe function in the caret package to do feature selection on a binomial GLM? I would like to pass the data frame of predictors and predictions and have it return the best model and features. If not is there another package I should use?

Answer 1

See ?lrFuncs for what you desire, although you are probably better off using regularization via glmnet than a feature selection wrapper method.

Max