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

Chris Gervais

12/13/2022, 9:05 PM
the Nixtla premium: NHiTS from
neuralforecast
consistently outperforming NHiTS from
pytorch-forecasting
in the wild lol
🙌 4
it's not a perfect comparison bc most of the hparams don't line up quite right between the two libraries but it is definitely noticeable
wondering if it has to do with your handling of lagged regressors, the
ptfc
version seems to limit you to lagged regressors from the target variable only
k

Kin Gtz. Olivares

12/14/2022, 12:48 AM
Hi @Chris Gervais That is cool, and as you noticed: NeuralForecast's NHITS allows for future, lagged and static exogenous variables. We made these exogenous variables available for all the models that we host. In the NBEATSx paper, exogenous variables gave us an advantage of 25% over the original NBEATS model.
2 Views