TimeSeriesForecastingJobConfig - Amazon SageMaker
Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China (PDF).


The collection of settings used by an AutoML job V2 for the time-series forecasting problem type.



The frequency of predictions in a forecast.

Valid intervals are an integer followed by Y (Year), M (Month), W (Week), D (Day), H (Hour), and min (Minute). For example, 1D indicates every day and 15min indicates every 15 minutes. The value of a frequency must not overlap with the next larger frequency. For example, you must use a frequency of 1H instead of 60min.

The valid values for each frequency are the following:

  • Minute - 1-59

  • Hour - 1-23

  • Day - 1-6

  • Week - 1-4

  • Month - 1-11

  • Year - 1

Type: String

Length Constraints: Minimum length of 1. Maximum length of 5.

Pattern: ^1Y|Y|([1-9]|1[0-1])M|M|[1-4]W|W|[1-6]D|D|([1-9]|1[0-9]|2[0-3])H|H|([1-9]|[1-5][0-9])min$

Required: Yes


The number of time-steps that the model predicts. The forecast horizon is also called the prediction length. The maximum forecast horizon is the lesser of 500 time-steps or 1/4 of the time-steps in the dataset.

Type: Integer

Valid Range: Minimum value of 1.

Required: Yes


The collection of components that defines the time-series.

Type: TimeSeriesConfig object

Required: Yes


Stores the configuration information for how model candidates are generated using an AutoML job V2.

Type: CandidateGenerationConfig object

Required: No


How long a job is allowed to run, or how many candidates a job is allowed to generate.

Type: AutoMLJobCompletionCriteria object

Required: No


A URL to the Amazon S3 data source containing additional selected features that complement the target, itemID, timestamp, and grouped columns set in TimeSeriesConfig. When not provided, the AutoML job V2 includes all the columns from the original dataset that are not already declared in TimeSeriesConfig. If provided, the AutoML job V2 only considers these additional columns as a complement to the ones declared in TimeSeriesConfig.

You can input FeatureAttributeNames (optional) in JSON format as shown below:

{ "FeatureAttributeNames":["col1", "col2", ...] }.

You can also specify the data type of the feature (optional) in the format shown below:

{ "FeatureDataTypes":{"col1":"numeric", "col2":"categorical" ... } }

Autopilot supports the following data types: numeric, categorical, text, and datetime.


These column keys must not include any column set in TimeSeriesConfig.

Type: String

Length Constraints: Maximum length of 1024.

Pattern: ^(https|s3)://([^/]+)/?(.*)$

Required: No


The quantiles used to train the model for forecasts at a specified quantile. You can specify quantiles from 0.01 (p1) to 0.99 (p99), by increments of 0.01 or higher. Up to five forecast quantiles can be specified. When ForecastQuantiles is not provided, the AutoML job uses the quantiles p10, p50, and p90 as default.

Type: Array of strings

Array Members: Minimum number of 1 item. Maximum number of 5 items.

Length Constraints: Minimum length of 2. Maximum length of 4.

Pattern: (^p[1-9]\d?$)

Required: No


The collection of holiday featurization attributes used to incorporate national holiday information into your forecasting model.

Type: Array of HolidayConfigAttributes objects

Array Members: Fixed number of 1 item.

Required: No


The transformations modifying specific attributes of the time-series, such as filling strategies for missing values.

Type: TimeSeriesTransformations object

Required: No

See Also

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