I am using XGBoost to predict a variable that is highly skewed and always is greater than zero. I did a significant search to see some materials for gamma objective function in XGBoost but I could not find anything being understandable for me. Considering that I have two options: 1. Use that gamma objective function without completely understanding it. 2. Transform the target variable to gamma space and fit a model.

Do you think that the second method is logical and it helps me to improve the performance of the model? I also wonder if you share some information about how gamma's objective function works.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.