1. Amazon SageMaker Developer Guide: "The Amazon SageMaker DeepAR forecasting algorithm is a supervised learning algorithm for forecasting scalar (one-dimensional) time series using a recurrent neural network (RNN)."
Source: AWS Documentation
Amazon SageMaker Developer Guide
"DeepAR forecasting algorithm".
2. Peer-Reviewed Academic Publication: The original paper on DeepAR states its purpose is to handle a large number of related time series. "We present DeepAR
a methodology for producing accurate probabilistic forecasts
based on training an auto-regressive recurrent network model on a large number of related time series."
Source: Salinas
D.
Flunkert
V.
Gasthaus
J.
& Januschowski
T. (2020). DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks. International Journal of Forecasting
36(3)
1181-1191. Section 1: Introduction. DOI: https://doi.org/10.1016/j.ijforecast.2019.07.001