Amazon Forecast Service

2023/02/01 - 3 updated api methods

Changes   This release will enable customer select INCREMENTAL as ImportModel in Forecast's CreateDatasetImportJob API. Verified latest SDK containing required attribute, following https://w.amazon.com/bin/view/AWS-Seer/Launch/Trebuchet/

2022/08/22 - 12 new api methods

Changes   releasing What-If Analysis APIs and update ARN regex pattern to be more strict in accordance with security recommendation

2022/06/01 - 10 updated api methods

Changes   Added Format field to Import and Export APIs in Amazon Forecast. Added TimeSeriesSelector to Create Forecast API.

2022/05/26 - 2 updated api methods

Changes   Introduced a new field in Auto Predictor as Time Alignment Boundary. It helps in aligning the timestamps generated during Forecast exports

2022/05/23 - 6 new 2 updated api methods

Changes   New APIs for Monitor that help you understand how your predictors perform over time.

2021/12/20 - 1 updated api methods

Changes   Adds ForecastDimensions field to the DescribeAutoPredictorResponse

2021/11/18 - 10 new 5 updated api methods

Changes   NEW CreateExplanability API that helps you understand how attributes such as price, promotion, etc. contributes to your forecasted values; NEW CreateAutoPredictor API that trains up to 40% more accurate forecasting model, saves up to 50% of retraining time, and provides model level explainability.

2021/09/07 - 3 updated api methods

Changes   Predictor creation now supports selecting an accuracy metric to optimize in AutoML and hyperparameter optimization. This release adds additional accuracy metrics for predictors - AverageWeightedQuantileLoss, MAPE and MASE.

2021/06/03 - 3 updated api methods

Changes   Added optional field AutoMLOverrideStrategy to CreatePredictor API that allows users to customize AutoML strategy. If provided in CreatePredictor request, this field is visible in DescribePredictor and GetAccuracyMetrics responses.

2021/05/21 - 1 updated api methods

Changes   Updated attribute statistics in DescribeDatasetImportJob response to support Long values

2021/04/30 - 1 new api methods

Changes   Added new DeleteResourceTree operation that helps in deleting all the child resources of a given resource including the given resource.

2021/04/22 - 3 updated api methods

Changes   This release adds EstimatedTimeRemaining minutes field to the DescribeDatasetImportJob, DescribePredictor, DescribeForecast API response which denotes the time remaining to complete the job IN_PROGRESS.

2021/03/03 - 1 new api methods

Changes   Added new StopResource operation that stops Amazon Forecast resource jobs that are in progress.

2020/12/08 - 4 updated api methods

Changes   This release adds support for the Amazon Forecast Weather Index which can increase forecasting accuracy by automatically including weather forecasts in demand forecasts.

2020/11/23 - 4 new api methods

Changes   Releasing the set of PredictorBacktestExportJob APIs which allow customers to export backtest values and item-level metrics data from Predictor training.

2020/11/11 - 3 updated api methods

Changes   Providing support of custom quantiles in CreatePredictor API.

2020/07/08 - 3 new 6 updated api methods

Changes   With this release, Amazon Forecast now supports the ability to add a tag to any resource via the launch of three new APIs: TagResouce, UntagResource and ListTagsForResource. A tag is a simple label consisting of a customer-defined key and an optional value allowing for easier resource management.

2019/11/22 - 3 updated api methods

Changes   This release adds two key updates to existing APIs. 1. Amazon Forecast can now generate forecasts in any quantile using the optional parameter forecastTypes in the CreateForecast API and 2. You can get additional details (metrics and relevant error messages) on your AutoML runs using the DescribePredictor and GetAccuracyMetrics APIs.

2019/08/21 - 26 new api methods

Changes   Amazon Forecast is a fully managed machine learning service that makes it easy for customers to generate accurate forecasts using their historical time-series data