The GLE node offers the ability to fit a wide variety of models, offering eight error distributions and nine link functions (though not all combinations would make sense). If you are not certain of the best model to use for your data, the node can be set to automatically try to identify this via selection of distribution and link functions. You can also use the GLE node for automated predictor selection for a given type of model, using forward stepwise, lasso, ridge, or elastic net methods, including automatic detection of two-way predictor interactions.
Like your visualization? Why not deploy it? For more information, see Deploy a model.