models#
Models for timeseries forecasting.
Modules
Timeseries models share a number of common characteristics. |
|
Baseline model. |
|
DeepAR: Probabilistic forecasting with autoregressive recurrent networks which is the one of the most popular forecasting algorithms and is often used as a baseline |
|
Simple models based on fully connected networks |
|
N-Beats model for timeseries forecasting without covariates. |
|
N-HiTS model for timeseries forecasting with covariates. |
|
Simple recurrent model - either with LSTM or GRU cells. |
|
The temporal fusion transformer is a powerful predictive model for forecasting timeseries |