This message was deleted.
# neural-forecast
s
This message was deleted.
c
Hi @Stefan Wiegand! Absolutely: 1. Yes, it is only based on the input window to prevent leakage from the future. 2. No, the training loss is scaled to improve stability (this is the most common approach). The validation loss is scaled back, as well as the forecasts of the
predict
method. 3. If you dont scale the data, then yes. With temporal normalization both series will have roughly the same scale, so they will both weight the same for the loss. (Note that in particular the MAE is more robust to scale, because the gradients are always +1/-1 regardless of the magnitude of the error.)
s
Great! Thank you very much for making this clear to me!