@Kin Gtz. Olivares Thanks! If I use the TFT model and set a high number of training steps (30-40 epochs), the model is somehow able to predict the winter peak that the global NBEATSx model could not predict, even if the predicted values are underestimated. Interestingly, if I train NBEATSx for the same large number of epochs, it is still unable to predict the peak. I do not know whether the difference is due to the different handling of exogenous variables or to the model architecture itself.
k
Kin Gtz. Olivares
06/22/2023, 2:29 PM
It is in the architecture
The NBEATSx does not have a static encoder
While TFT does
Kin Gtz. Olivares
06/22/2023, 2:44 PM
You can help NBEATSx and TFT by feeding a SeasonalNaive “anchor” prediction that catches the winter peaks, if you have enough information for your series