POST

/#X-Amz-Target=AmazonForecast.CreatePredictorBacktestExportJob

http://forecast.{region}.amazonaws.com/#X-Amz-Target=AmazonForecast.CreatePredictorBacktestExportJob

Exports backtest forecasts and accuracy metrics generated by the <a>CreateAutoPredictor</a> or <a>CreatePredictor</a> operations. Two folders containing CSV or Parquet files are exported to your specified S3 bucket. The export file names will match the following conventions: <code><ExportJobName>_<ExportTimestamp>_<PartNumber>.csv</code> The <ExportTimestamp> component is in Java SimpleDate format (yyyy-MM-ddTHH-mm-ssZ). You must specify a <a>DataDestination</a> object that includes an Amazon S3 bucket and an Identity and Access Management (IAM) role that Amazon Forecast can assume to access the Amazon S3 bucket. For more information, see <a>aws-forecast-iam-roles</a>. <note> The <code>Status</code> of the export job must be <code>ACTIVE</code> before you can access the export in your Amazon S3 bucket. To get the status, use the <a>DescribePredictorBacktestExportJob</a> operation. </note>

Access Token Required: API Key

Responses

{
  "success": true,
  "data": {
    "id": "abc123",
    "created_at": "2025-01-01T00:00:00Z"
  }
}

{
  "success": false,
  "error": {
    "code": "VALIDATION_ERROR",
    "message": "Invalid request parameters"
  }
}

Language

CredentialsAPI KEY

API Key

Enter token below to save for later

cURL Request

1curl --request POST \
2     --url 'http://forecast.{region}.amazonaws.com/#X-Amz-Target=AmazonForecast.CreatePredictorBacktestExportJob' \
3     --header 'accept: application/json' \
4     --header 'content-type: application/json'

Response

1{
2  "success": true,
3  "data": {
4    "id": "abc123",
5    "created_at": "2025-01-01T00:00:00Z"
6  }
7}