I'm training a XGBoost Regressor to predict price which has a highly right skewed distribution. (all prices are positive) I took log transformation on the target thinking it would help to 1) stable the variance and 2) introduce non-linearities. And the log-transformed target yields very good MAPE/SMAPE. However, when I transformed the prediction back by taking exponential, and calculated MAPE/SMAPE, it is even worse than non-transformed target (original price).

Could not wrap my head around this, would appreciate any help.



The results of the model trained based on the transformed target to the log space are misleading. Briefly, the log transformation shrinks the variance of the outcomes. Hence, the log transformation makes the model appears better even though it does nothing different.

I would strongly suggest you to take a look at this post too. Log-Transforming target var for training a Random Forest Regressor


Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.