The data configuration for your dataset group and any additional datasets.

Undocumented member.

Create an Explainability resource for the predictor.

An array of dimension (field) names that specify how to group the generated forecast.

For example, if you are generating forecasts for item sales across all your stores, and your dataset contains a store_id field, you would specify store_id as a dimension to group sales forecasts for each store.

The frequency of predictions in a forecast.

Valid intervals are Y (Year), M (Month), W (Week), D (Day), H (Hour), 30min (30 minutes), 15min (15 minutes), 10min (10 minutes), 5min (5 minutes), and 1min (1 minute). For example, "Y" indicates every year and "5min" indicates every five minutes.

The frequency must be greater than or equal to the TARGET_TIME_SERIES dataset frequency.

When a RELATED_TIME_SERIES dataset is provided, the frequency must be equal to the RELATED_TIME_SERIES dataset frequency.

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 TARGET_TIME_SERIES dataset length. If you are retraining an existing AutoPredictor, then the maximum forecast horizon is the lesser of 500 time-steps or 1/3 of the TARGET_TIME_SERIES dataset length.

If you are upgrading to an AutoPredictor or retraining an existing AutoPredictor, you cannot update the forecast horizon parameter. You can meet this requirement by providing longer time-series in the dataset.

The forecast types used to train a predictor. You can specify up to five forecast types. Forecast types can be quantiles from 0.01 to 0.99, by increments of 0.01 or higher. You can also specify the mean forecast with mean.

The configuration details for predictor monitoring. Provide a name for the monitor resource to enable predictor monitoring.

Predictor monitoring allows you to see how your predictor's performance changes over time. For more information, see Predictor Monitoring.

The accuracy metric used to optimize the predictor.

The ARN of the predictor to retrain or upgrade. This parameter is only used when retraining or upgrading a predictor. When creating a new predictor, do not specify a value for this parameter.

When upgrading or retraining a predictor, only specify values for the ReferencePredictorArn and PredictorName. The value for PredictorName must be a unique predictor name.

Optional metadata to help you categorize and organize your predictors. Each tag consists of a key and an optional value, both of which you define. Tag keys and values are case sensitive.

The following restrictions apply to tags:

• For each resource, each tag key must be unique and each tag key must have one value.
• Maximum number of tags per resource: 50.
• Maximum key length: 128 Unicode characters in UTF-8.
• Maximum value length: 256 Unicode characters in UTF-8.
• Accepted characters: all letters and numbers, spaces representable in UTF-8, and + - = . _ : / @. If your tagging schema is used across other services and resources, the character restrictions of those services also apply.
• Key prefixes cannot include any upper or lowercase combination of aws: or AWS:. Values can have this prefix. If a tag value has aws as its prefix but the key does not, Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit. You cannot edit or delete tag keys with this prefix.

The time boundary Forecast uses to align and aggregate any data that doesn't align with your forecast frequency. Provide the unit of time and the time boundary as a key value pair. For more information on specifying a time boundary, see Specifying a Time Boundary. If you don't provide a time boundary, Forecast uses a set of Default Time Boundaries.

A unique name for the predictor

The Amazon Resource Name (ARN) of the predictor.

The response's http status code.

The frequency of data collection. This parameter is required for RELATED_TIME_SERIES datasets.

Valid intervals are Y (Year), M (Month), W (Week), D (Day), H (Hour), 30min (30 minutes), 15min (15 minutes), 10min (10 minutes), 5min (5 minutes), and 1min (1 minute). For example, "D" indicates every day and "15min" indicates every 15 minutes.

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.

The optional metadata that you apply to the dataset to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define.

The following basic restrictions apply to tags:

• Maximum number of tags per resource - 50.
• For each resource, each tag key must be unique, and each tag key can have only one value.
• Maximum key length - 128 Unicode characters in UTF-8.
• Maximum value length - 256 Unicode characters in UTF-8.
• If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @.
• Tag keys and values are case sensitive.
• Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.

A name for the dataset.

The domain associated with the dataset. When you add a dataset to a dataset group, this value and the value specified for the Domain parameter of the CreateDatasetGroup operation must match.

The Domain and DatasetType that you choose determine the fields that must be present in the training data that you import to the dataset. For example, if you choose the RETAIL domain and TARGET_TIME_SERIES as the DatasetType, Amazon Forecast requires item_id, timestamp, and demand fields to be present in your data. For more information, see Importing datasets.

The dataset type. Valid values depend on the chosen Domain.

The schema for the dataset. The schema attributes and their order must match the fields in your data. The dataset Domain and DatasetType that you choose determine the minimum required fields in your training data. For information about the required fields for a specific dataset domain and type, see Dataset Domains and Dataset Types.

The Amazon Resource Name (ARN) of the dataset.

The response's http status code.

An array of Amazon Resource Names (ARNs) of the datasets that you want to include in the dataset group.

The optional metadata that you apply to the dataset group to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define.

The following basic restrictions apply to tags:

• Maximum number of tags per resource - 50.
• For each resource, each tag key must be unique, and each tag key can have only one value.
• Maximum key length - 128 Unicode characters in UTF-8.
• Maximum value length - 256 Unicode characters in UTF-8.
• If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @.
• Tag keys and values are case sensitive.
• Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.

A name for the dataset group.

The domain associated with the dataset group. When you add a dataset to a dataset group, this value and the value specified for the Domain parameter of the CreateDataset operation must match.

The Domain and DatasetType that you choose determine the fields that must be present in training data that you import to a dataset. For example, if you choose the RETAIL domain and TARGET_TIME_SERIES as the DatasetType, Amazon Forecast requires that item_id, timestamp, and demand fields are present in your data. For more information, see Dataset groups.

The Amazon Resource Name (ARN) of the dataset group.

The response's http status code.

The format of the imported data, CSV or PARQUET. The default value is CSV.

The format of the geolocation attribute. The geolocation attribute can be formatted in one of two ways:

• LAT_LONG - the latitude and longitude in decimal format (Example: 47.61_-122.33).
• CC_POSTALCODE (US Only) - the country code (US), followed by the 5-digit ZIP code (Example: US_98121).

The optional metadata that you apply to the dataset import job to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define.

The following basic restrictions apply to tags:

• Maximum number of tags per resource - 50.
• For each resource, each tag key must be unique, and each tag key can have only one value.
• Maximum key length - 128 Unicode characters in UTF-8.
• Maximum value length - 256 Unicode characters in UTF-8.
• If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @.
• Tag keys and values are case sensitive.
• Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.

A single time zone for every item in your dataset. This option is ideal for datasets with all timestamps within a single time zone, or if all timestamps are normalized to a single time zone.

Refer to the Joda-Time API for a complete list of valid time zone names.

The format of timestamps in the dataset. The format that you specify depends on the DataFrequency specified when the dataset was created. The following formats are supported

• "yyyy-MM-dd"

  For the following data frequencies: Y, M, W, and D

• "yyyy-MM-dd HH:mm:ss"

  For the following data frequencies: H, 30min, 15min, and 1min; and optionally, for: Y, M, W, and D

If the format isn't specified, Amazon Forecast expects the format to be "yyyy-MM-dd HH:mm:ss".

Automatically derive time zone information from the geolocation attribute. This option is ideal for datasets that contain timestamps in multiple time zones and those timestamps are expressed in local time.

The name for the dataset import job. We recommend including the current timestamp in the name, for example, 20190721DatasetImport. This can help you avoid getting a ResourceAlreadyExistsException exception.

The Amazon Resource Name (ARN) of the Amazon Forecast dataset that you want to import data to.

The location of the training data to import and an AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the data. The training data must be stored in an Amazon S3 bucket.

If encryption is used, DataSource must include an AWS Key Management Service (KMS) key and the IAM role must allow Amazon Forecast permission to access the key. The KMS key and IAM role must match those specified in the EncryptionConfig parameter of the CreateDataset operation.

The Amazon Resource Name (ARN) of the dataset import job.

The response's http status code.

Undocumented member.

Create an Explainability visualization that is viewable within the AWS console.

If TimePointGranularity is set to SPECIFIC, define the last time point for the Explainability.

Use the following timestamp format: yyyy-MM-ddTHH:mm:ss (example: 2015-01-01T20:00:00)

Undocumented member.

If TimePointGranularity is set to SPECIFIC, define the first point for the Explainability.

Use the following timestamp format: yyyy-MM-ddTHH:mm:ss (example: 2015-01-01T20:00:00)

Optional metadata to help you categorize and organize your resources. Each tag consists of a key and an optional value, both of which you define. Tag keys and values are case sensitive.

The following restrictions apply to tags:

• For each resource, each tag key must be unique and each tag key must have one value.
• Maximum number of tags per resource: 50.
• Maximum key length: 128 Unicode characters in UTF-8.
• Maximum value length: 256 Unicode characters in UTF-8.
• Accepted characters: all letters and numbers, spaces representable in UTF-8, and + - = . _ : / @. If your tagging schema is used across other services and resources, the character restrictions of those services also apply.
• Key prefixes cannot include any upper or lowercase combination of aws: or AWS:. Values can have this prefix. If a tag value has aws as its prefix but the key does not, Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit. You cannot edit or delete tag keys with this prefix.

A unique name for the Explainability.

The Amazon Resource Name (ARN) of the Predictor or Forecast used to create the Explainability.

The configuration settings that define the granularity of time series and time points for the Explainability.

The Amazon Resource Name (ARN) of the Explainability.

The response's http status code.

The format of the exported data, CSV or PARQUET.

Optional metadata to help you categorize and organize your resources. Each tag consists of a key and an optional value, both of which you define. Tag keys and values are case sensitive.

The following restrictions apply to tags:

• For each resource, each tag key must be unique and each tag key must have one value.
• Maximum number of tags per resource: 50.
• Maximum key length: 128 Unicode characters in UTF-8.
• Maximum value length: 256 Unicode characters in UTF-8.
• Accepted characters: all letters and numbers, spaces representable in UTF-8, and + - = . _ : / @. If your tagging schema is used across other services and resources, the character restrictions of those services also apply.
• Key prefixes cannot include any upper or lowercase combination of aws: or AWS:. Values can have this prefix. If a tag value has aws as its prefix but the key does not, Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit. You cannot edit or delete tag keys with this prefix.

A unique name for the Explainability export.

The Amazon Resource Name (ARN) of the Explainability to export.

Undocumented member.

The Amazon Resource Name (ARN) of the export.

The response's http status code.

The quantiles at which probabilistic forecasts are generated. __You can currently specify up to 5 quantiles per forecast__. Accepted values include 0.01 to 0.99 (increments of .01 only) and mean. The mean forecast is different from the median (0.50) when the distribution is not symmetric (for example, Beta and Negative Binomial).

The default quantiles are the quantiles you specified during predictor creation. If you didn't specify quantiles, the default values are ["0.1", "0.5", "0.9"].

The optional metadata that you apply to the forecast to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define.

The following basic restrictions apply to tags:

• Maximum number of tags per resource - 50.
• For each resource, each tag key must be unique, and each tag key can have only one value.
• Maximum key length - 128 Unicode characters in UTF-8.
• Maximum value length - 256 Unicode characters in UTF-8.
• If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @.
• Tag keys and values are case sensitive.
• Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.

Defines the set of time series that are used to create the forecasts in a TimeSeriesIdentifiers object.

The TimeSeriesIdentifiers object needs the following information:

• DataSource

• Format

• Schema

A name for the forecast.

The Amazon Resource Name (ARN) of the predictor to use to generate the forecast.

The Amazon Resource Name (ARN) of the forecast.

The response's http status code.

The format of the exported data, CSV or PARQUET. The default value is CSV.

The optional metadata that you apply to the forecast export job to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define.

The following basic restrictions apply to tags:

• Maximum number of tags per resource - 50.
• For each resource, each tag key must be unique, and each tag key can have only one value.
• Maximum key length - 128 Unicode characters in UTF-8.
• Maximum value length - 256 Unicode characters in UTF-8.
• If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @.
• Tag keys and values are case sensitive.
• Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.

The name for the forecast export job.

The Amazon Resource Name (ARN) of the forecast that you want to export.

The location where you want to save the forecast and an AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the location. The forecast must be exported to an Amazon S3 bucket.

If encryption is used, Destination must include an AWS Key Management Service (KMS) key. The IAM role must allow Amazon Forecast permission to access the key.

The Amazon Resource Name (ARN) of the export job.

The response's http status code.

A list of tags to apply to the monitor resource.

The name of the monitor resource.

The Amazon Resource Name (ARN) of the predictor to monitor.

The Amazon Resource Name (ARN) of the monitor resource.

The response's http status code.

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/CNN-QR

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

• arn:aws:forecast:::algorithm/ETS

• arn:aws:forecast:::algorithm/NPTS

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

The LatencyOptimized AutoML override strategy is only available in private beta. Contact AWS Support or your account manager to learn more about access privileges.

Used to overide the default AutoML strategy, which is to optimize predictor accuracy. To apply an AutoML strategy that minimizes training time, use LatencyOptimized.

This parameter is only valid for predictors trained using AutoML.

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.

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.

Specifies the forecast types used to train a predictor. You can specify up to five forecast types. Forecast types can be quantiles from 0.01 to 0.99, by increments of 0.01 or higher. You can also specify the mean forecast with mean.

The default value is ["0.10", "0.50", "0.9"].

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 aws-forecast-choosing-recipes.

If you included the HPOConfig object, you must set PerformHPO to true.

The accuracy metric used to optimize the predictor.

Whether to perform AutoML. When Amazon Forecast performs AutoML, it evaluates the algorithms it provides and chooses the best algorithm and configuration for your training dataset.

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

Set PerformAutoML to true to have Amazon Forecast perform AutoML. This is a good option if you aren't sure which algorithm is suitable for your training data. In this case, PerformHPO must be false.

Whether to perform hyperparameter optimization (HPO). HPO finds optimal hyperparameter values for your training data. The process of performing HPO is known as running 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, optionally, supply the HyperParameterTuningJobConfig object. The tuning job specifies a metric to optimize, which hyperparameters participate in tuning, and the valid range for each tunable hyperparameter. In this case, you are required to specify an algorithm and PerformAutoML must be false.

The following algorithms support HPO:

• DeepAR+
• CNN-QR

The optional metadata that you apply to the predictor to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define.

The following basic restrictions apply to tags:

• Maximum number of tags per resource - 50.
• For each resource, each tag key must be unique, and each tag key can have only one value.
• Maximum key length - 128 Unicode characters in UTF-8.
• Maximum value length - 256 Unicode characters in UTF-8.
• If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @.
• Tag keys and values are case sensitive.
• Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.

The hyperparameters to override for model training. The hyperparameters that you can override are listed in the individual algorithms. For the list of supported algorithms, see aws-forecast-choosing-recipes.

A name for the predictor.

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.

The maximum forecast horizon is the lesser of 500 time-steps or 1/3 of the TARGET_TIME_SERIES dataset length.

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

The featurization configuration.

The Amazon Resource Name (ARN) of the predictor.

The response's http status code.

The format of the exported data, CSV or PARQUET. The default value is CSV.

Optional metadata to help you categorize and organize your backtests. Each tag consists of a key and an optional value, both of which you define. Tag keys and values are case sensitive.

The following restrictions apply to tags:

• For each resource, each tag key must be unique and each tag key must have one value.
• Maximum number of tags per resource: 50.
• Maximum key length: 128 Unicode characters in UTF-8.
• Maximum value length: 256 Unicode characters in UTF-8.
• Accepted characters: all letters and numbers, spaces representable in UTF-8, and + - = . _ : / @. If your tagging schema is used across other services and resources, the character restrictions of those services also apply.
• Key prefixes cannot include any upper or lowercase combination of aws: or AWS:. Values can have this prefix. If a tag value has aws as its prefix but the key does not, Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit. You cannot edit or delete tag keys with this prefix.

The name for the backtest export job.

The Amazon Resource Name (ARN) of the predictor that you want to export.

Undocumented member.

The Amazon Resource Name (ARN) of the predictor backtest export job that you want to export.

The response's http status code.

A list of tags to apply to the what if forecast.

Defines the set of time series that are used in the what-if analysis with a TimeSeriesIdentifiers object. What-if analyses are performed only for the time series in this object.

The TimeSeriesIdentifiers object needs the following information:

• DataSource

• Format

• Schema

The name of the what-if analysis. Each name must be unique.

The Amazon Resource Name (ARN) of the baseline forecast.

The Amazon Resource Name (ARN) of the what-if analysis.

The response's http status code.

A list of tags to apply to the what if forecast.

The replacement time series dataset, which contains the rows that you want to change in the related time series dataset. A replacement time series does not need to contain all rows that are in the baseline related time series. Include only the rows (measure-dimension combinations) that you want to include in the what-if forecast. This dataset is merged with the original time series to create a transformed dataset that is used for the what-if analysis.

This dataset should contain the items to modify (such as item_id or workforce_type), any relevant dimensions, the timestamp column, and at least one of the related time series columns. This file should not contain duplicate timestamps for the same time series.

Timestamps and item_ids not included in this dataset are not included in the what-if analysis.

The transformations that are applied to the baseline time series. Each transformation contains an action and a set of conditions. An action is applied only when all conditions are met. If no conditions are provided, the action is applied to all items.

The name of the what-if forecast. Names must be unique within each what-if analysis.

The Amazon Resource Name (ARN) of the what-if analysis.

The Amazon Resource Name (ARN) of the what-if forecast.

The response's http status code.

The format of the exported data, CSV or PARQUET.

A list of tags to apply to the what if forecast.

The name of the what-if forecast to export.

The list of what-if forecast Amazon Resource Names (ARNs) to export.

The location where you want to save the forecast and an AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the location. The forecast must be exported to an Amazon S3 bucket.

If encryption is used, Destination must include an AWS Key Management Service (KMS) key. The IAM role must allow Amazon Forecast permission to access the key.

The Amazon Resource Name (ARN) of the what-if forecast.

The response's http status code.

The Amazon Resource Name (ARN) of the dataset to delete.

The Amazon Resource Name (ARN) of the dataset group to delete.

The Amazon Resource Name (ARN) of the dataset import job to delete.

The Amazon Resource Name (ARN) of the Explainability resource to delete.

The Amazon Resource Name (ARN) of the Explainability export to delete.

The Amazon Resource Name (ARN) of the forecast to delete.

The Amazon Resource Name (ARN) of the forecast export job to delete.

The Amazon Resource Name (ARN) of the monitor resource to delete.

The Amazon Resource Name (ARN) of the predictor to delete.

The Amazon Resource Name (ARN) of the predictor backtest export job to delete.

The Amazon Resource Name (ARN) of the parent resource to delete. All child resources of the parent resource will also be deleted.

The Amazon Resource Name (ARN) of the what-if analysis that you want to delete.

The Amazon Resource Name (ARN) of the what-if forecast that you want to delete.

The Amazon Resource Name (ARN) of the what-if forecast export that you want to delete.

The Amazon Resource Name (ARN) of the predictor.

The timestamp of the CreateAutoPredictor request.

The data configuration for your dataset group and any additional datasets.

An array of the ARNs of the dataset import jobs used to import training data for the predictor.

Undocumented member.

The estimated time remaining in minutes for the predictor training job to complete.

Provides the status and ARN of the Predictor Explainability.

An array of dimension (field) names that specify the attributes used to group your time series.

The frequency of predictions in a forecast.

Valid intervals are Y (Year), M (Month), W (Week), D (Day), H (Hour), 30min (30 minutes), 15min (15 minutes), 10min (10 minutes), 5min (5 minutes), and 1min (1 minute). For example, "Y" indicates every year and "5min" indicates every five minutes.

The number of time-steps that the model predicts. The forecast horizon is also called the prediction length.

The forecast types used during predictor training. Default value is ["0.1","0.5","0.9"].

The last time the resource was modified. The timestamp depends on the status of the job:

• CREATE_PENDING - The CreationTime.
• CREATE_IN_PROGRESS - The current timestamp.
• CREATE_STOPPING - The current timestamp.
• CREATE_STOPPED - When the job stopped.
• ACTIVE or CREATE_FAILED - When the job finished or failed.

In the event of an error, a message detailing the cause of the error.

A object with the Amazon Resource Name (ARN) and status of the monitor resource.

The accuracy metric used to optimize the predictor.

The Amazon Resource Name (ARN) of the predictor

The name of the predictor.

The ARN and state of the reference predictor. This parameter is only valid for retrained or upgraded predictors.

The status of the predictor. States include:

• ACTIVE

• CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
• CREATE_STOPPING, CREATE_STOPPED
• DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED

The time boundary Forecast uses when aggregating data.

The response's http status code.

The Amazon Resource Name (ARN) of the dataset.

When the dataset was created.

The frequency of data collection.

Valid intervals are Y (Year), M (Month), W (Week), D (Day), H (Hour), 30min (30 minutes), 15min (15 minutes), 10min (10 minutes), 5min (5 minutes), and 1min (1 minute). For example, "M" indicates every month and "30min" indicates every 30 minutes.

The Amazon Resource Name (ARN) of the dataset.

The name of the dataset.

The dataset type.

The domain associated with the dataset.

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

When you create a dataset, LastModificationTime is the same as CreationTime. While data is being imported to the dataset, LastModificationTime is the current time of the DescribeDataset call. After a CreateDatasetImportJob operation has finished, LastModificationTime is when the import job completed or failed.

An array of SchemaAttribute objects that specify the dataset fields. Each SchemaAttribute specifies the name and data type of a field.

The status of the dataset. States include:

• ACTIVE

• CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
• DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
• UPDATE_PENDING, UPDATE_IN_PROGRESS, UPDATE_FAILED

The UPDATE states apply while data is imported to the dataset from a call to the CreateDatasetImportJob operation and reflect the status of the dataset import job. For example, when the import job status is CREATE_IN_PROGRESS, the status of the dataset is UPDATE_IN_PROGRESS.

The Status of the dataset must be ACTIVE before you can import training data.

The response's http status code.

The Amazon Resource Name (ARN) of the dataset group.

When the dataset group was created.

An array of Amazon Resource Names (ARNs) of the datasets contained in the dataset group.

The ARN of the dataset group.

The name of the dataset group.

The domain associated with the dataset group.

When the dataset group was created or last updated from a call to the UpdateDatasetGroup operation. While the dataset group is being updated, LastModificationTime is the current time of the DescribeDatasetGroup call.

The status of the dataset group. States include:

• ACTIVE

• CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
• DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
• UPDATE_PENDING, UPDATE_IN_PROGRESS, UPDATE_FAILED

The UPDATE states apply when you call the UpdateDatasetGroup operation.

The Status of the dataset group must be ACTIVE before you can use the dataset group to create a predictor.

The response's http status code.

The Amazon Resource Name (ARN) of the dataset import job.

When the dataset import job was created.

The size of the dataset in gigabytes (GB) after the import job has finished.

The location of the training data to import and an AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the data.

If encryption is used, DataSource includes an AWS Key Management Service (KMS) key.

The Amazon Resource Name (ARN) of the dataset that the training data was imported to.

The ARN of the dataset import job.

The name of the dataset import job.

The estimated time remaining in minutes for the dataset import job to complete.

Statistical information about each field in the input data.

The format of the imported data, CSV or PARQUET.

The format of the geolocation attribute. Valid Values:"LAT_LONG" and "CC_POSTALCODE".

The last time the resource was modified. The timestamp depends on the status of the job:

• CREATE_PENDING - The CreationTime.
• CREATE_IN_PROGRESS - The current timestamp.
• CREATE_STOPPING - The current timestamp.
• CREATE_STOPPED - When the job stopped.
• ACTIVE or CREATE_FAILED - When the job finished or failed.

If an error occurred, an informational message about the error.

The status of the dataset import job. States include:

• ACTIVE

• CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
• DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
• CREATE_STOPPING, CREATE_STOPPED

The single time zone applied to every item in the dataset

The format of timestamps in the dataset. The format that you specify depends on the DataFrequency specified when the dataset was created. The following formats are supported

• "yyyy-MM-dd"

  For the following data frequencies: Y, M, W, and D

• "yyyy-MM-dd HH:mm:ss"

  For the following data frequencies: H, 30min, 15min, and 1min; and optionally, for: Y, M, W, and D

Whether TimeZone is automatically derived from the geolocation attribute.

The response's http status code.

The Amazon Resource Name (ARN) of the Explaianability to describe.

When the Explainability resource was created.

Undocumented member.

Whether the visualization was enabled for the Explainability resource.

If TimePointGranularity is set to SPECIFIC, the last time point in the Explainability.

The estimated time remaining in minutes for the CreateExplainability job to complete.

The Amazon Resource Name (ARN) of the Explainability.

The configuration settings that define the granularity of time series and time points for the Explainability.

The name of the Explainability.

The last time the resource was modified. The timestamp depends on the status of the job:

• CREATE_PENDING - The CreationTime.
• CREATE_IN_PROGRESS - The current timestamp.
• CREATE_STOPPING - The current timestamp.
• CREATE_STOPPED - When the job stopped.
• ACTIVE or CREATE_FAILED - When the job finished or failed.

If an error occurred, a message about the error.

The Amazon Resource Name (ARN) of the Predictor or Forecast used to create the Explainability resource.

Undocumented member.

If TimePointGranularity is set to SPECIFIC, the first time point in the Explainability.

The status of the Explainability resource. States include:

• ACTIVE

• CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
• CREATE_STOPPING, CREATE_STOPPED
• DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED

The response's http status code.

The Amazon Resource Name (ARN) of the Explainability export.

When the Explainability export was created.

Undocumented member.

The Amazon Resource Name (ARN) of the Explainability export.

The Amazon Resource Name (ARN) of the Explainability export.

The name of the Explainability export.

The format of the exported data, CSV or PARQUET.

The last time the resource was modified. The timestamp depends on the status of the job:

• CREATE_PENDING - The CreationTime.
• CREATE_IN_PROGRESS - The current timestamp.
• CREATE_STOPPING - The current timestamp.
• CREATE_STOPPED - When the job stopped.
• ACTIVE or CREATE_FAILED - When the job finished or failed.

Information about any errors that occurred during the export.

The status of the Explainability export. States include:

• ACTIVE

• CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
• CREATE_STOPPING, CREATE_STOPPED
• DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED

The response's http status code.

The Amazon Resource Name (ARN) of the forecast.

When the forecast creation task was created.

The ARN of the dataset group that provided the data used to train the predictor.

The estimated time remaining in minutes for the forecast job to complete.

The forecast ARN as specified in the request.

The name of the forecast.

The quantiles at which probabilistic forecasts were generated.

The last time the resource was modified. The timestamp depends on the status of the job:

• CREATE_PENDING - The CreationTime.
• CREATE_IN_PROGRESS - The current timestamp.
• CREATE_STOPPING - The current timestamp.
• CREATE_STOPPED - When the job stopped.
• ACTIVE or CREATE_FAILED - When the job finished or failed.

If an error occurred, an informational message about the error.

The ARN of the predictor used to generate the forecast.

The status of the forecast. States include:

• ACTIVE

• CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
• CREATE_STOPPING, CREATE_STOPPED
• DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED

The Status of the forecast must be ACTIVE before you can query or export the forecast.

The time series to include in the forecast.

The response's http status code.

The Amazon Resource Name (ARN) of the forecast export job.

When the forecast export job was created.

The path to the Amazon Simple Storage Service (Amazon S3) bucket where the forecast is exported.

The Amazon Resource Name (ARN) of the exported forecast.

The ARN of the forecast export job.

The name of the forecast export job.

The format of the exported data, CSV or PARQUET.

The last time the resource was modified. The timestamp depends on the status of the job:

• CREATE_PENDING - The CreationTime.
• CREATE_IN_PROGRESS - The current timestamp.
• CREATE_STOPPING - The current timestamp.
• CREATE_STOPPED - When the job stopped.
• ACTIVE or CREATE_FAILED - When the job finished or failed.

If an error occurred, an informational message about the error.

The status of the forecast export job. States include:

• ACTIVE

• CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
• CREATE_STOPPING, CREATE_STOPPED
• DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED

The Status of the forecast export job must be ACTIVE before you can access the forecast in your S3 bucket.

The response's http status code.

The Amazon Resource Name (ARN) of the monitor resource to describe.

Metrics you can use as a baseline for comparison purposes. Use these values you interpret monitoring results for an auto predictor.

The timestamp for when the monitor resource was created.

The estimated number of minutes remaining before the monitor resource finishes its current evaluation.

The state of the monitor's latest evaluation.

The timestamp of the latest evaluation completed by the monitor.

The timestamp of the latest modification to the monitor.

An error message, if any, for the monitor.

The Amazon Resource Name (ARN) of the monitor resource described.

The name of the monitor.

The Amazon Resource Name (ARN) of the auto predictor being monitored.

The status of the monitor resource.

The response's http status code.

The Amazon Resource Name (ARN) of the predictor that you want information about.

The Amazon Resource Name (ARN) of the algorithm used for model training.

When PerformAutoML is specified, the ARN of the chosen algorithm.

The LatencyOptimized AutoML override strategy is only available in private beta. Contact AWS Support or your account manager to learn more about access privileges.

The AutoML strategy used to train the predictor. Unless LatencyOptimized is specified, the AutoML strategy optimizes predictor accuracy.

This parameter is only valid for predictors trained using AutoML.

When the model training task was created.

An array of the ARNs of the dataset import jobs used to import training data for the predictor.

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.

The estimated time remaining in minutes for the predictor training job to complete.

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.

The featurization configuration.

The number of time-steps of the forecast. The forecast horizon is also called the prediction length.

The forecast types used during predictor training. Default value is ["0.1","0.5","0.9"]

The hyperparameter override values for the algorithm.

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

Whether the predictor was created with CreateAutoPredictor.

The last time the resource was modified. The timestamp depends on the status of the job:

• CREATE_PENDING - The CreationTime.
• CREATE_IN_PROGRESS - The current timestamp.
• CREATE_STOPPING - The current timestamp.
• CREATE_STOPPED - When the job stopped.
• ACTIVE or CREATE_FAILED - When the job finished or failed.

If an error occurred, an informational message about the error.

The accuracy metric used to optimize the predictor.

Whether the predictor is set to perform AutoML.

Whether the predictor is set to perform hyperparameter optimization (HPO).

The ARN of the predictor.

Details on the the status and results of the backtests performed to evaluate the accuracy of the predictor. You specify the number of backtests to perform when you call the operation.

The name of the predictor.

The status of the predictor. States include:

• ACTIVE

• CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
• DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
• CREATE_STOPPING, CREATE_STOPPED

The Status of the predictor must be ACTIVE before you can use the predictor to create a forecast.

The default training parameters or overrides selected during model training. When running AutoML or choosing HPO with CNN-QR or DeepAR+, the optimized values for the chosen hyperparameters are returned. For more information, see aws-forecast-choosing-recipes.

The response's http status code.

The Amazon Resource Name (ARN) of the predictor backtest export job.

When the predictor backtest export job was created.

Undocumented member.

The format of the exported data, CSV or PARQUET.

The last time the resource was modified. The timestamp depends on the status of the job:

• CREATE_PENDING - The CreationTime.
• CREATE_IN_PROGRESS - The current timestamp.
• CREATE_STOPPING - The current timestamp.
• CREATE_STOPPED - When the job stopped.
• ACTIVE or CREATE_FAILED - When the job finished or failed.

Information about any errors that may have occurred during the backtest export.

The Amazon Resource Name (ARN) of the predictor.

The Amazon Resource Name (ARN) of the predictor backtest export job.

The name of the predictor backtest export job.