https://github.com/nixtla logo
#neural-forecast
Title
# neural-forecast
l

Luis Huergo

08/24/2023, 7:00 PM
Hi everybody, I am new here and I might be asking a question which was already asked. I couldn't find any matches though, so I hope you'll forgive me. Here is the question: I am intending to develop a time series model in the fashion of our old econometric "distributed lags models". That means, that the forecast (even a nowcast) ist done only with past values of other variables. The own time series is not available for prediction. LSTMs and TCNs can handle it without difficulty but I would like to implement a TFT and a nbeats for I have the feeling that the structures might be interesting for the task. Any hint on how to move on will be much appreciated!
c

Cristian (Nixtla)

08/24/2023, 7:51 PM
Hi @Luis Huergo! Yes, you can do it with all models. Set the hyperparameter
exclude_insample_y=True
when you instantiate a model, and it will only use other variables to produce the forecasts
you still need to pass the
y
variable to the training data, because it will use it for the training loss.