Amazon Forecast
Developer Guide

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

The Amazon Forecast API underwent significant changes during the scheduled maintenance that occurred from 7/22/19 through 7/23/19. As part of maintenance, all Forecast resources (datasets, predictors, and forecasts) were deleted.

To use the new APIs, you must install new JSON service files by following Steps 3 through 6 in Set Up the AWS CLI and modify your existing code to reflect the syntax changes. We have revised our GitHub notebooks to help you understand how to interact with the new APIs. If you use only the console, no changes are necessary.

For a table describing the API changes, see API Changes in Amazon Forecast.

If you have questions, contact .


Creates an Amazon Forecast predictor.

In the request, you provide a dataset group and either specify an algorithm or let Amazon Forecast choose the algorithm for you using AutoML. If you specify an algorithm, you also can override algorithm-specific hyperparameters.

If you set PerformAutoML to true, Amazon Forecast evaluates each algorithm and chooses the one that minimizes the objective function. The objective function is defined as the mean of the weighted p10, p50, and p90 quantile losses. For more information, see EvaluationResult.

Amazon Forecast uses the chosen algorithm to train a model using the latest version of the datasets in the specified dataset group. The result is called a predictor. You then generate a forecast using the CreateForecast operation.

After training a model, the CreatePredictor operation also evaluates it. To see the evaluation metrics, use the GetAccuracyMetrics operation. Always review the evaluation metrics before deciding to use the predictor to generate a forecast.

Optionally, you can specify a featurization configuration to fill and aggragate the data fields in the TARGET_TIME_SERIES dataset to improve model training. For more information, see FeaturizationConfig.

To get a list of all your predictors, use the ListPredictors operation.

For more information, see Predictors.


The Status of the predictor must be ACTIVE, signifying that training has completed, before you can use the predictor to create a forecast. Use the DescribePredictor operation to get the status.

Request Syntax

{ "AlgorithmArn": "string", "EncryptionConfig": { "KMSKeyArn": "string", "RoleArn": "string" }, "EvaluationParameters": { "BackTestWindowOffset": number, "NumberOfBacktestWindows": number }, "FeaturizationConfig": { "Featurizations": [ { "AttributeName": "string", "FeaturizationPipeline": [ { "FeaturizationMethodName": "string", "FeaturizationMethodParameters": { "string" : "string" } } ] } ], "ForecastDimensions": [ "string" ], "ForecastFrequency": "string", "TrainingSubsampleRatio": number }, "ForecastHorizon": number, "HPOConfig": { "ParameterRanges": { "CategoricalParameterRanges": [ { "Name": "string", "Values": [ "string" ] } ], "ContinuousParameterRanges": [ { "MaxValue": number, "MinValue": number, "Name": "string", "ScalingType": "string" } ], "IntegerParameterRanges": [ { "MaxValue": number, "MinValue": number, "Name": "string", "ScalingType": "string" } ] } }, "InputDataConfig": { "DatasetGroupArn": "string", "SupplementaryFeatures": [ { "Name": "string", "Value": "string" } ] }, "PerformAutoML": boolean, "PerformHPO": boolean, "PredictorName": "string", "TrainingParameters": { "string" : "string" } }

Request Parameters

The request accepts the following data in JSON format.


The Amazon Resource Name (ARN) of the algorithm to use for model training. Required if PerformAutoML is not set to true.

Supported algorithms

  • arn:aws:forecast:::algorithm/ARIMA

  • arn:aws:forecast:::algorithm/Deep_AR_Plus

    - supports hyperparameter optimization (HPO)

  • arn:aws:forecast:::algorithm/ETS

  • arn:aws:forecast:::algorithm/NPTS

  • arn:aws:forecast:::algorithm/Prophet

Type: String

Length Constraints: Maximum length of 256.

Pattern: ^[a-zA-Z0-9\-\_\.\/\:]+$

Required: No


An AWS Key Management Service (KMS) key and the AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key.

Type: EncryptionConfig object

Required: No


Used to override the default evaluation parameters of the specified algorithm. Amazon Forecast evaluates a predictor by splitting a dataset into training data and testing data. The evaluation parameters define how to perform the split and the number of iterations.

Type: EvaluationParameters object

Required: No


The featurization configuration.

Type: FeaturizationConfig object

Required: Yes


Specifies the number of time-steps that the model is trained to predict. The forecast horizon is also called the prediction length.

For example, if you configure a dataset for daily data collection (using the DataFrequency parameter of the CreateDataset operation) and set the forecast horizon to 10, the model returns predictions for 10 days.

Type: Integer

Required: Yes


Provides hyperparameter override values for the algorithm. If you don't provide this parameter, Amazon Forecast uses default values. The individual algorithms specify which hyperparameters support hyperparameter optimization (HPO). For more information, see Choosing an Amazon Forecast Algorithm.

Type: HyperParameterTuningJobConfig object

Required: No


Describes the dataset group that contains the data to use to train the predictor.

Type: InputDataConfig object

Required: Yes


Whether to perform AutoML. The default value is false. In this case, you are required to specify an algorithm.

If you want Amazon Forecast to evaluate the algorithms it provides and choose the best algorithm and configuration for your training dataset, set PerformAutoML to true. This is a good option if you aren't sure which algorithm is suitable for your application.

Type: Boolean

Required: No


Whether to perform hyperparameter optimization (HPO). HPO finds optimal hyperparameter values for your training data. The process of performing HPO is known as a hyperparameter tuning job.

The default value is false. In this case, Amazon Forecast uses default hyperparameter values from the chosen algorithm.

To override the default values, set PerformHPO to true and supply the HyperParameterTuningJobConfig object. The tuning job specifies an objective metric, the hyperparameters to optimize, and the valid range for each hyperparameter.

The following algorithms support HPO:

  • DeepAR+

Type: Boolean

Required: No


A name for the predictor.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 63.

Pattern: ^[a-zA-Z0-9][a-zA-Z0-9_]*

Required: Yes


The training parameters to override for model training. The parameters that you can override are listed in the individual algorithms in Choosing an Amazon Forecast Algorithm.

Type: String to string map

Key Length Constraints: Maximum length of 256.

Key Pattern: ^[a-zA-Z0-9\-\_\.\/\[\]\,\\]+$

Value Length Constraints: Maximum length of 256.

Value Pattern: ^[a-zA-Z0-9\-\_\.\/\[\]\,\"\\\s]+$

Required: No

Response Syntax

{ "PredictorArn": "string" }

Response Elements

If the action is successful, the service sends back an HTTP 200 response.

The following data is returned in JSON format by the service.


The Amazon Resource Name (ARN) of the predictor.

Type: String

Length Constraints: Maximum length of 256.

Pattern: ^[a-zA-Z0-9\-\_\.\/\:]+$



We can't process the request because it includes an invalid value or a value that exceeds the valid range.

HTTP Status Code: 400


The limit on the number of requests per second has been exceeded.

HTTP Status Code: 400


There is already a resource with that Amazon Resource Name (ARN). Try again with a different ARN.

HTTP Status Code: 400


The specified resource is in use.

HTTP Status Code: 400


We can't find a resource with that Amazon Resource Name (ARN). Check the ARN and try again.

HTTP Status Code: 400

See Also

For more information about using this API in one of the language-specific AWS SDKs, see the following: