Hello, I have a question regarding the lift value that I shoud expect on the first decile derived from a Random Forest Models. In details, I computed a HP random Forest model using SAS Miner to identify the propensity to buy a product. As result, I have found that my model produce a lift chart value about 9 (on a first decile) in the validation set. In your opinion and experiences, isn't that value too high? Should I expect a smaller value? As each of the trainig and validation lift chart are the same, I tend to exclude overfitting; is there somthing else should I controll to be sure my model is well done? Thank you very much in advance!
... View more
