#neural-forecast

Title

p

Pandula

04/06/2022, 8:47 AMHello everyone, nice to be here! Big thanks to the team for their contribution(s).
Quick question, to be familiar with the package I am planning to use it to model a multi-step multivariate ts problem; any recommendations on which model to try out first? I apologise if this is answered somewhere already.

đŸ‘€ 1

c

Cristian (Nixtla)

04/06/2022, 2:54 PMHello Pandula, thanks for joining!
All the models in our neuralforecast library are multi-step. The hyperparameter n_time_out controls the forecast horizon. I recommend trying the N-HiTS or RNN models first. They are univariate, but can be used for multivariate problems as well since they will share parameters for all the ts (one model will be used to forecast all ts).
Check our colab example: https://colab.research.google.com/drive/1WjBbQzaivQhOldGolzymOtLmo6QX4Ieg#scrollTo=HXKT2-fpUD0Z. We use the N-HiTS model in a multivariate multi-step problem.

k

Kin Gtz. Olivares

04/06/2022, 2:55 PMNeuralForecast's models take as input your target data with all your series

`Y_df`

and exogenous data `X_df`

with columns `unique_id, ds`

p

Pandula

04/06/2022, 9:24 PMhey thank you both for the help and suggestion. I tried it and got it to work, so thatâ€™s a win! I am trying to figure out how to work with

`X_df`

now, specially how to structure it. I guess `unique_id`

is used to differentiate between different series? If I keep the `ds`

and `unique_id`

columns plus all other exogenous vars in the `X_df`

, it would work right? (apologies for not trying it out and asking, itâ€™s pretty late and I only saw this message now)
I scanned through the notebooks in `/nbs`

and saw examples, would they be the best source of documentation to refer to?`one model will be used to forecast all ts)`

does it mean the model act similar to VAR models or each ts is separately forecasted as univariate ts?c

Cristian (Nixtla)

04/06/2022, 9:29 PMeach ts is separately forecasted

p

Pandula

04/07/2022, 6:18 AMThanks **@Cristian (Nixtla)**!

2 Views