SageMaker provides algorithms that are tailored to the analysis of time-series data for forecasting product demand, server loads, webpage requests, and more.
- DeepAR Forecasting Algorithm—a supervised learning algorithm for forecasting scalar (one-dimensional) time series using recurrent neural networks (RNN).
| Algorithm name | Channel name | Training input mode | File type | Instance class | Parallelizable |
|---|---|---|---|---|---|
| DeepAR Forecasting | train and (optionally) test | File | JSON Lines or Parquet | GPU or CPU | Yes |