---
title: "POST /#X-Amz-Target=AmazonForecast.CreateExplainability"
method: POST
path: "/#X-Amz-Target=AmazonForecast.CreateExplainability"
---

# POST /#X-Amz-Target=AmazonForecast.CreateExplainability

`POST /#X-Amz-Target=AmazonForecast.CreateExplainability`

<note> <p>Explainability is only available for Forecasts and Predictors generated from an AutoPredictor (<a>CreateAutoPredictor</a>)</p> </note> <p>Creates an Amazon Forecast Explainability.</p> <p>Explainability helps you better understand how the attributes in your datasets impact forecast. Amazon Forecast uses a metric called Impact scores to quantify the relative impact of each attribute and determine whether they increase or decrease forecast values.</p> <p>To enable Forecast Explainability, your predictor must include at least one of the following: related time series, item metadata, or additional datasets like Holidays and the Weather Index.</p> <p>CreateExplainability accepts either a Predictor ARN or Forecast ARN. To receive aggregated Impact scores for all time series and time points in your datasets, provide a Predictor ARN. To receive Impact scores for specific time series and time points, provide a Forecast ARN.</p> <p> <b>CreateExplainability with a Predictor ARN</b> </p> <note> <p>You can only have one Explainability resource per predictor. If you already enabled <code>ExplainPredictor</code> in <a>CreateAutoPredictor</a>, that predictor already has an Explainability resource.</p> </note> <p>The following parameters are required when providing a Predictor ARN:</p> <ul> <li> <p> <code>ExplainabilityName</code> - A unique name for the Explainability.</p> </li> <li> <p> <code>ResourceArn</code> - The Arn of the predictor.</p> </li> <li> <p> <code>TimePointGranularity</code> - Must be set to “ALL”.</p> </li> <li> <p> <code>TimeSeriesGranularity</code> - Must be set to “ALL”.</p> </li> </ul> <p>Do not specify a value for the following parameters:</p> <ul> <li> <p> <code>DataSource</code> - Only valid when TimeSeriesGranularity is “SPECIFIC”.</p> </li> <li> <p> <code>Schema</code> - Only valid when TimeSeriesGranularity is “SPECIFIC”.</p> </li> <li> <p> <code>StartDateTime</code> - Only valid when TimePointGranularity is “SPECIFIC”.</p> </li> <li> <p> <code>EndDateTime</code> - Only valid when TimePointGranularity is “SPECIFIC”.</p> </li> </ul> <p> <b>CreateExplainability with a Forecast ARN</b> </p> <note> <p>You can specify a maximum of 50 time series and 500 time points.</p> </note> <p>The following parameters are required when providing a Predictor ARN:</p> <ul> <li> <p> <code>ExplainabilityName</code> - A unique name for the Explainability.</p> </li> <li> <p> <code>ResourceArn</code> - The Arn of the forecast.</p> </li> <li> <p> <code>TimePointGranularity</code> - Either “ALL” or “SPECIFIC”.</p> </li> <li> <p> <code>TimeSeriesGranularity</code> - Either “ALL” or “SPECIFIC”.</p> </li> </ul> <p>If you set TimeSeriesGranularity to “SPECIFIC”, you must also provide the following:</p> <ul> <li> <p> <code>DataSource</code> - The S3 location of the CSV file specifying your time series.</p> </li> <li> <p> <code>Schema</code> - The Schema defines the attributes and attribute types listed in the Data Source.</p> </li> </ul> <p>If you set TimePointGranularity to “SPECIFIC”, you must also provide the following:</p> <ul> <li> <p> <code>StartDateTime</code> - The first timestamp in the range of time points.</p> </li> <li> <p> <code>EndDateTime</code> - The last timestamp in the range of time points.</p> </li> </ul>

## Headers

- `X-Amz-Target` 'AmazonForecast.CreateExplainability', required

## Request body

- CreateExplainabilityRequest
  - `ExplainabilityName` string, required — A unique name for the Explainability.
  - `ResourceArn` string, required — The Amazon Resource Name (ARN) of the Predictor or Forecast used to create the Explainability.
  - `ExplainabilityConfig` object, required — The configuration settings that define the granularity of time series and time points for the Explainability.
    - `TimeSeriesGranularity` 'ALL' | 'SPECIFIC', required — <p>To create an Explainability for all time series in your datasets, use <code>ALL</code>. To create an Explainability for specific time series in your datasets, use <code>SPECIFIC</code>.</p> <p>Specify time series by uploading a CSV or Parquet file to an Amazon S3 bucket and set the location within the <a>DataDestination</a> data type.</p>
    - `TimePointGranularity` 'ALL' | 'SPECIFIC', required — <p>To create an Explainability for all time points in your forecast horizon, use <code>ALL</code>. To create an Explainability for specific time points in your forecast horizon, use <code>SPECIFIC</code>.</p> <p>Specify time points with the <code>StartDateTime</code> and <code>EndDateTime</code> parameters within the <a>CreateExplainability</a> operation.</p>
  - `DataSource` DataSource — The source of your data, an Identity and Access Management (IAM) role that allows Amazon Forecast to access the data and, optionally, an Key Management Service (KMS) key.
    - `S3Config` object, required — The path to the data stored in an Amazon Simple Storage Service (Amazon S3) bucket along with the credentials to access the data.
      - `Path` string, required — The path to an Amazon Simple Storage Service (Amazon S3) bucket or file(s) in an Amazon S3 bucket.
      - `RoleArn` string, required — <p>The ARN of the Identity and Access Management (IAM) role that Amazon Forecast can assume to access the Amazon S3 bucket or files. If you provide a value for the <code>KMSKeyArn</code> key, the role must allow access to the key.</p> <p>Passing a role across Amazon Web Services accounts is not allowed. If you pass a role that isn't in your account, you get an <code>InvalidInputException</code> error.</p>
      - `KMSKeyArn` string — The Amazon Resource Name (ARN) of an Key Management Service (KMS) key.
  - `Schema` Schema — Defines the fields of a dataset.
    - `Attributes` SchemaAttribute[] — An array of attributes specifying the name and type of each field in a dataset.
      - `AttributeName` string — The name of the dataset field.
      - `AttributeType` 'string' | 'integer' | 'float' | 'timestamp' | 'geolocation' — <p>The data type of the field.</p> <p>For a related time series dataset, other than date, item_id, and forecast dimensions attributes, all attributes should be of numerical type (integer/float).</p>
  - `EnableVisualization` boolean — Create an Explainability visualization that is viewable within the Amazon Web Services console.
  - `StartDateTime` string — <p>If <code>TimePointGranularity</code> is set to <code>SPECIFIC</code>, define the first point for the Explainability.</p> <p>Use the following timestamp format: yyyy-MM-ddTHH:mm:ss (example: 2015-01-01T20:00:00)</p>
  - `EndDateTime` string — <p>If <code>TimePointGranularity</code> is set to <code>SPECIFIC</code>, define the last time point for the Explainability.</p> <p>Use the following timestamp format: yyyy-MM-ddTHH:mm:ss (example: 2015-01-01T20:00:00)</p>
  - `Tags` Tag[] — <p>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.</p> <p>The following restrictions apply to tags:</p> <ul> <li> <p>For each resource, each tag key must be unique and each tag key must have one value.</p> </li> <li> <p>Maximum number of tags per resource: 50.</p> </li> <li> <p>Maximum key length: 128 Unicode characters in UTF-8.</p> </li> <li> <p>Maximum value length: 256 Unicode characters in UTF-8.</p> </li> <li> <p>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. </p> </li> <li> <p>Key prefixes cannot include any upper or lowercase combination of <code>aws:</code> or <code>AWS:</code>. Values can have this prefix. If a tag value has <code>aws</code> 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 <code>aws</code> do not count against your tags per resource limit. You cannot edit or delete tag keys with this prefix.</p> </li> </ul>
    - `Key` string, password, required — One part of a key-value pair that makes up a tag. A <code>key</code> is a general label that acts like a category for more specific tag values.
    - `Value` string, password, required — The optional part of a key-value pair that makes up a tag. A <code>value</code> acts as a descriptor within a tag category (key).

## Response `200`

Success

- CreateExplainabilityResponse
  - `ExplainabilityArn` string — The Amazon Resource Name (ARN) of the Explainability.

## Other responses

- `480` — InvalidInputException
- `481` — ResourceAlreadyExistsException
- `482` — ResourceNotFoundException
- `483` — ResourceInUseException
- `484` — LimitExceededException

---

[API](https://skmtc.net/aws/apis/forecast.md) · [All operations](https://skmtc.net/aws/apis/forecast/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/aws/forecast/versions/3d1c872d2ac9/schema)