What’s your take on normalization strategies for neural models? Specially when predicting for multiple time series with different scales? I’ve been normalizing per group, but seems that pytorch-forecasting encourages normalizing per observation? Have you experimented with different approaches?

@Kin Gtz. Olivares?

In our experience normalizing per time-series is the best alternative

I think what I meant is the same as you mean with ‘per time series’. Ie, if you have sales per store/department, you’ll normalize per store/department right?

@Daniel Falbel : You might one to take a look to the (N-BEATSx normalization)[https://github.com/cchallu/nbeatsx/blob/main/src/utils/experiment/utils_experiment.py] strategies. We have had very good experience using the Mean Absolute Deviation (MAD) instead of the classic std normalization. MAD is robust to outliers.

Yes, its the same

Cool! Thanks for the pointers @Kin Gtz. Olivares ! Will try that too