Generating a forecast
In Chapter 4, Training a Predictor with AutoML, and Chapter 5, Customizing Your Predictor Training, we focused on the first step of the forecasting process: looking back in historical data to establish a baseline and uncover trends that may continue in the future. In Amazon Forecast, this is done by training a predictor (your trained model). Once you have a model ready to be used, you can use Amazon Forecast to generate predictions for your time series: this is the highlighted area on the right side in the following figure:
In other words, you will use Amazon Forecast to generate future values in a timeframe beyond the last date available in your ingested dataset. In Chapter 3, Creating a Project and Ingesting Your Data, you ingested data from 2012-07-01 to 2013-06-30. You are now going to generate predictions for data starting on 2013-07-01.
In the next section, you are going to learn how...