Posted On: Mar 9, 2021
Amazon Forecast uses machine learning (ML) to generate more accurate demand forecasts, without requiring any prior ML experience. Forecast brings the same technology used at Amazon.com to developers as a fully managed service, removing the need to manage resources or rebuild your systems.
You can get started generating forecasts through Amazon Forecast by following these three steps: 1) import your data, 2) train and evaluate a predictor, and 3) generate forecasts. Today, we announce that you will have more flexibility to manage your Amazon Forecast workflows and experimentation. Now, if you have mistakenly started a job or misconfigured a workflow, you can stop these in-progress resource workflows. Previously, without being able to stop in-progress APIs, you would have had to wait for the job to complete and you would incur associated charges. Now, when you import datasets, train predictors, export predictor backtest results, create forecasts, and export forecast results, you have more flexibility to manage your Amazon Forecast workflows.
To get started with this capability, read through our blog here, see guidance at Stopping Resource , or go through the notebook in our GitHub repo that walks you through how to use the Amazon Forecast Stop Resource APIs. You can use this capability in all Regions where Amazon Forecast is publicly available. For more information about Region availability, see AWS Regional Services.