Amazon Forecast
Developer Guide

This is prerelease documentation for a service in preview release. It is subject to change.

How Amazon Forecast Works

When creating forecasting projects in Amazon Forecast, you work with the following resources:

  • Datasets and Dataset Groups – You create an Amazon Forecast dataset and import your data. Amazon Forecast algorithms use your datasets to train custom forecasting models, called predictors.

  • Predictors – Predictors are custom models trained on your data. You can train a predictor by choosing a prebuilt recipe (which provides an algorithm and the data featurization associated with the algorithm) or by asking Amazon Forecast to pick the best algorithm by choosing the AutoML option.

  • Forecasts – You can deploy predictors and generate forecasts for your time-series.