models

Models for timeseries forecasting.

Modules

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