DeepAR - Torch

DeepAR is an autoregressive recurrent neural network that forecasts probability distributions for the next forecast horizon values given the preceding context length values. It also uses lagged values and time features, automatically computed based on the selected time frequency. This implementation relies on Torch.

Training parameters

Patience

The number of allowed epochs with no improvement after which the learning rate will be reduced.

Batch size

The size of the batches to be used for training and prediction.

Epochs

Use default nb. of batches per epoch

Default value is the number of batches for which on average each time step appears in one sample per epoch.

Number of batches per epoch

Random state

Using a fixed random seed allows for reproducible result.

Model parameters

Use default context length

Set the context length to the model's default value (context length = forecast horizon).

Scale target values

For each time series, rescale the target by its average absolute value.

Number of parallel samples

Number of evaluation samples per time series, to increase parallelism during inference.