https://github.com/nixtla logo
l

lbfan

06/28/2023, 5:06 AM
Is there method I could use to predict time series of length more than
h
? for example, I train a nbeatsx model which have a predict length
h
of 24, now I want to predict the time series with length of 48, how could I do it?
k

Kin Gtz. Olivares

06/28/2023, 12:51 PM
Hi @Ibfan, For the moment all NeuralForecast architectures use a direct multi-step forecasting strategy. For this reason the decoders of the networks are restricted to output a fixed horizon
h
. What we have done in the past was fit a long enough horizon and trim for other forecasting needs.
l

lbfan

06/29/2023, 1:28 AM
Thanks @Kin Gtz. Olivares, are we planning to add new function/method to support more flexible prediction window?