Create an AutoML job for time-series forecasting using the API

By default, your Autopilot job trains a pre-defined list of algorithms on your dataset. However, you can provide a subset of the default selection of algorithms.

For time-series forecasting, you must choose TimeSeriesForecastingJobConfig as the type of AutoMLProblemTypeConfig.

Then, you can specify an array of selected AutoMLAlgorithms in the AlgorithmsConfig attribute of CandidateGenerationConfig.

The following is an example of an AlgorithmsConfig attribute listing exactly three algorithms ("cnn-qr", "prophet", "arima") in its AutoMLAlgorithms field.

{
   "AutoMLProblemTypeConfig": {
        "TimeSeriesForecastingJobConfig": {
          "CandidateGenerationConfig": {
            "AlgorithmsConfig":[
               {"AutoMLAlgorithms":["cnn-qr", "prophet", "arima"]}
            ]
         },
       },
     },
  }

For the list of available algorithms for time-series forecasting, see AutoMLAlgorithms. For details on each algorithm, see Algorithms support for time-series forecasting.

Autopilot trains 6 models candidates with your target time-series, then combines these models using a stacking ensemble method to create an optimal forecasting model for a given objective metric. Each Autopilot forecasting model generates a probabilistic forecast by producing forecasts at quantiles between P1 and P99. These quantiles are used to account for forecast uncertainty. By default, forecasts will be generated for the 0.1 (p10), 0.5 (p50), and 0.9 (p90). You can choose to specify your own quantiles.

In Autopilot, you can specify up to five forecast quantiles from 0.01 (p1) to 0.99 (p99), by increments of 0.01 or higher in the ForecastQuantiles attribute of TimeSeriesForecastingJobConfig.

In the following example, you are setting up a daily 10th, 25th, 50th, 75th, and 90th percentile forecast for the expected quantity or level of demand of specific items over a period of 20 days.

"AutoMLProblemTypeConfig": { 
        "ForecastFrequency": "D",
        "ForecastHorizon": 20,
        "ForecastQuantiles": ["p10", "p25", "p50", "p75", "p90"],
        "TimeSeriesConfig": {
            "TargetAttributeName": "demand",
            "TimestampAttributeName": "timestamp",
            "ItemIdentifierAttributeName": "item_id"
        },

To create a forecast model (also referred to as the best model candidate from your experiment), you must specify a forecast frequency. The forecast frequency determines the frequency of predictions in your forecasts. For example, monthly sales forecasts. Autopilot best model can generate forecasts for data frequencies that are higher than the frequency at which your data is recorded.

During training, Autopilot aggregates any data that does not align with the forecast frequency you specify. For example, you might have some daily data but specify a weekly forecast frequency. Autopilot aligns the daily data based on the week that it belongs in. Autopilot then combines it into single record for each week.

During aggregation, the default transformation method is to sum the data. You can configure the aggregation when you create your AutoML job in the Transformations attribute of TimeSeriesForecastingJobConfig. The supported aggregation methods are sum (default), avg, first, min, max. Aggregation is only supported for the target column.

In the following example, you configure the aggregation to calculate the average of the individual promo forecasts to provide the final aggregated forecast values.

"Transformations": {
            "Aggregation": {
                "promo": "avg"
            }
        }

Autopilot provides a number of filling methods to handle missing values in the target and other numeric columns of your time-series datasets. For information on the list of supported filling methods and their available filling logic, see Handle missing values.

You configure your filling strategy in the Transformations attribute of TimeSeriesForecastingJobConfig when creating your AutoML job.

To set a filling method, you need to provide a key-value pair:

You can specify multiple filling methods for a single column.

To set a specific value for the filling method, you should set the fill parameter to the desired filling method value (for example "backfill" : "value"), and define the actual filling value in an additional parameter suffixed with "_value". For example, to set backfill to a value of 2, you must include two parameters: "backfill": "value" and "backfill_value":"2".

In the following example, you specify the filling strategy for the incomplete data column, "price" as follows: All missing values between the first data point of an item and the last are set to 0 after which all missing values are filled with the value 2 until the end date of the dataset.

"Transformations": {
            "Filling": {
                "price": {
                        "middlefill" : "zero",
                        "backfill" : "value",
                        "backfill_value": "2"
                }
            }
        }

Autopilot produces accuracy metrics to evaluate the model candidates and help you choose which to use to generate forecasts. When you run a time-series forecasting experiment, you can either choose AutoML to let Autopilot optimize the predictor for you, or you can manually choose an algorithm for your predictor.

By default, Autopilot uses the Average Weighted Quantile Loss. However, you can configure the objective metric when you create your AutoML job in the MetricName attribute of AutoMLJobObjective.

For the list of available algorithms, see Algorithms support for time-series forecasting.

In Autopilot, you can incorporate a feature-engineered dataset of national holiday information to your time-series. Autopilot provide native support for the holiday calendars of over 250 countries. After you choose a country, Autopilot applies that country’s holiday calendar to every item in your dataset during training. This allows the model to identify patterns associated with specific holidays.

You can enable the holiday featurization when you create your AutoML job by passing an HolidayConfigAttributes object to the HolidayConfig attribute of TimeSeriesForecastingJobConfig. The HolidayConfigAttributes object contains the two letters CountryCode attribute that determines the country of the public national holiday calendar used to augment your time-series dataset.

Refer to Country Codes for the list of supported calendars and their corresponding country code.

Autopilot allows you to automatically deploy your forecast model to an endpoint. To enable automatic deployment for the best model candidate of an AutoML job, include a ModelDeployConfig in the AutoML job request. This allows the deployment of the best model to a SageMaker AI endpoint. Below are the available configurations for customization.

You can configure your AutoML job V2 to automatically initiate a remote job on Amazon EMR Serverless when additional compute resources are needed to process large datasets. By seamlessly transitioning to EMR Serverless when required, the AutoML job can handle datasets that would otherwise exceed the initially provisioned resources, without any manual intervention from you. EMR Serverless is available for the tabular and time series problem types. We recommend setting up this option for time-series datasets larger than 30 GB.

To allow your AutoML job V2 to automatically transition to EMR Serverless for large dataset, you need to provide an EmrServerlessComputeConfig object, which includes an ExecutionRoleARN field, to the AutoMLComputeConfig of the AutoML job V2 input request.

The ExecutionRoleARN is the ARN of the IAM role granting the AutoML job V2 the necessary permissions to run EMR Serverless jobs.

This role should have the following trust relationship:

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Principal": {
                "Service": "emr-serverless.amazonaws.com"
            },
            "Action": "sts:AssumeRole"
        }
    ]
}

And grant the permissions to:

The IAM policy defined in the provided JSON document grants those permissions:

{
    "Version": "2012-10-17",
    "Statement": [{
           "Sid": "EMRServerlessCreateApplicationOperation",
           "Effect": "Allow",
           "Action": "emr-serverless:CreateApplication",
           "Resource": "arn:aws:emr-serverless:*:*:/*",
            "Condition": {
                "StringEquals": {
                    "aws:RequestTag/sagemaker:is-canvas-resource": "True",
                    "aws:ResourceAccount": "${aws:PrincipalAccount}"
                }
            }
        },
        {
            "Sid": "EMRServerlessListApplicationOperation",
            "Effect": "Allow",
            "Action": "emr-serverless:ListApplications",
            "Resource": "arn:aws:emr-serverless:*:*:/*",
            "Condition": {
                "StringEquals": {
                    "aws:ResourceAccount": "${aws:PrincipalAccount}"
                }
            }
        },
        {
            "Sid": "EMRServerlessApplicationOperations",
            "Effect": "Allow",
            "Action": [
                "emr-serverless:UpdateApplication",
                "emr-serverless:GetApplication"
            ],
            "Resource": "arn:aws:emr-serverless:*:*:/applications/*",
            "Condition": {
                "StringEquals": {
                    "aws:ResourceTag/sagemaker:is-canvas-resource": "True",
                    "aws:ResourceAccount": "${aws:PrincipalAccount}"
                }
            }
        },
        {
            "Sid": "EMRServerlessStartJobRunOperation",
            "Effect": "Allow",
            "Action": "emr-serverless:StartJobRun",
            "Resource": "arn:aws:emr-serverless:*:*:/applications/*",
            "Condition": {
                "StringEquals": {
                    "aws:RequestTag/sagemaker:is-canvas-resource": "True",
                    "aws:ResourceAccount": "${aws:PrincipalAccount}"
                }
            }
        },
        {
            "Sid": "EMRServerlessListJobRunOperation",
            "Effect": "Allow",
            "Action": "emr-serverless:ListJobRuns",
            "Resource": "arn:aws:emr-serverless:*:*:/applications/*",
            "Condition": {
                "StringEquals": {
                    "aws:ResourceTag/sagemaker:is-canvas-resource": "True",
                    "aws:ResourceAccount": "${aws:PrincipalAccount}"
                }
            }
        },
        {
            "Sid": "EMRServerlessJobRunOperations",
            "Effect": "Allow",
            "Action": [
                "emr-serverless:GetJobRun",
                "emr-serverless:CancelJobRun"
            ],
            "Resource": "arn:aws:emr-serverless:*:*:/applications/*/jobruns/*",
            "Condition": {
                "StringEquals": {
                    "aws:ResourceTag/sagemaker:is-canvas-resource": "True",
                    "aws:ResourceAccount": "${aws:PrincipalAccount}"
                }
            }
        },
        {
            "Sid": "EMRServerlessTagResourceOperation",
            "Effect": "Allow",
            "Action": "emr-serverless:TagResource",
            "Resource": "arn:aws:emr-serverless:*:*:/*",
            "Condition": {
                "StringEquals": {
                    "aws:RequestTag/sagemaker:is-canvas-resource": "True",
                    "aws:ResourceAccount": "${aws:PrincipalAccount}"
                }
            }
        },
        {
            "Sid": "IAMPassOperationForEMRServerless",
            "Effect": "Allow",
            "Action": "iam:PassRole",
            "Resource": "arn:aws:iam::*:role/EMRServerlessRuntimeRole-*",
            "Condition": {
                "StringEquals": {
                    "iam:PassedToService": "emr-serverless.amazonaws.com",
                    "aws:ResourceAccount": "${aws:PrincipalAccount}"
                }
            }
         }
    ]
}