Amazon Forecast

Amazon Forecast is a fully managed service that uses machine learning to deliver highly accurate forecasts. It analyzes your historical time-series data and automatically selects the right machine learning algorithms to generate accurate forecasts with no machine learning expertise required.

1 APIs 7 Features

ForecastingMachine LearningPredictive AnalyticsTime Series

APIs

Amazon Forecast API

The Amazon Forecast API provides programmatic access to create and manage datasets, predictors, forecasts, and export jobs for time-series forecasting using machine learning mod...

Collections

Amazon Forecast API

POSTMAN

Amazon Forecast API

OPEN

Arazzo Workflows

Amazon Forecast End to End Pipeline

Create a dataset, dataset group, predictor, and forecast in a single chained pass.

ARAZZO

Amazon Forecast Export Forecast

Create a forecast, wait until ACTIVE, export it to S3, and read its tags.

ARAZZO

Amazon Forecast Generate Forecast

Create a forecast from a predictor, poll until ACTIVE, and tag it.

ARAZZO

Amazon Forecast Group Then Train

Create a dataset group, wait until ACTIVE, then train a predictor on it.

ARAZZO

Amazon Forecast Predict and Forecast

Train a predictor, wait until ACTIVE, then create a forecast and wait until ACTIVE.

ARAZZO

Amazon Forecast Provision Dataset Group

Create a dataset group, poll the listing until it is ACTIVE, and tag it.

ARAZZO

Amazon Forecast Provision Dataset

Create a dataset, poll until it becomes ACTIVE, and tag it.

ARAZZO

Amazon Forecast Register Dataset to Group

Create a dataset, wait until ACTIVE, then create a dataset group containing it.

ARAZZO

Amazon Forecast Train Predictor

Create a predictor, poll the listing until it is ACTIVE, and tag it.

ARAZZO

Pricing Plans

Amazon Forecast Plans Pricing

3 plans

PLANS

Rate Limits

Amazon Forecast Rate Limits

5 limits

RATE LIMITS

FinOps

Amazon Forecast Finops

FINOPS

Features

AutoML

Automatically evaluates and selects from over 60 ML algorithms to find the best fit for your time-series data.

Probabilistic Forecasts

Generates quantile forecasts (p10, p50, p90) to estimate demand uncertainty and plan inventory buffers.

Domain-Specific Models

Pre-built domain configurations for retail, workforce, traffic, and cloud capacity forecasting.

Related Time Series

Incorporate external factors (price, promotions, holidays) as related time-series data to improve accuracy.

HPO (Hyperparameter Optimization)

Automatic tuning of model hyperparameters to maximize forecast accuracy.

Explainability

Forecast Explainability reports show which features most impact each individual forecast.

S3 Export

Export forecast results to Amazon S3 in CSV format for downstream consumption.

Use Cases

Retail Demand Forecasting

Predict item-level sales for inventory planning and replenishment across stores.

Workforce Capacity Planning

Forecast staffing needs for contact centers and seasonal workforce management.

Cloud Resource Forecasting

Predict EC2 capacity requirements to optimize reserved instance purchases.

Supply Chain Optimization

Forecast component and raw material demand to reduce stockouts and carrying costs.

Financial Revenue Forecasting

Project revenue by product, region, and channel for financial planning.

Energy Load Forecasting

Predict electricity load and generation requirements for grid balancing.

Semantic Vocabularies

Amazon Forecast Context

5 classes · 15 properties

JSON-LD

API Governance Rules

Amazon Forecast API Rules

25 rules · 7 errors 15 warnings 3 info

SPECTRAL

JSON Structure

Amazon Forecast Dataset Group Structure

0 properties

JSON STRUCTURE

Amazon Forecast Dataset Structure

0 properties

JSON STRUCTURE

Amazon Forecast Forecast Structure

0 properties

JSON STRUCTURE

Amazon Forecast Predictor Structure

0 properties

JSON STRUCTURE

Amazon Forecast Tag Structure

0 properties

JSON STRUCTURE

Example Payloads

Amazon Forecast Dataset Example

8 fields

EXAMPLE

Amazon Forecast Dataset Group Example

7 fields

EXAMPLE

Amazon Forecast Forecast Example

7 fields

EXAMPLE

Amazon Forecast Predictor Example

10 fields

EXAMPLE

Amazon Forecast Tag Example

2 fields

EXAMPLE

Resources

PostmanWorkspace

PostmanWorkspace

Documentation

TermsOfService

PrivacyPolicy

GitHubOrganization

GitHubOrganization

StackOverflow

SpectralRules

Sources

opencollection: 1.0.0
info:
  name: Amazon Forecast API
  version: '2018-06-26'
request:
  auth:
    type: apikey
    key: Authorization
    value: '{{Authorization}}'
    placement: header
items:
- info:
    name: Datasets
    type: folder
  items:
  - info:
      name: List Datasets
      type: http
    http:
      method: GET
      url: https://forecast.{region}.amazonaws.com/datasets
      params:
      - name: maxResults
        value: ''
        type: query
        description: Maximum results to return.
      - name: nextToken
        value: ''
        type: query
        description: Pagination token.
    docs: Returns a list of datasets created using CreateDataset.
  - info:
      name: Create Dataset
      type: http
    http:
      method: POST
      url: https://forecast.{region}.amazonaws.com/datasets
      body:
        type: json
        data: '{}'
    docs: Creates an Amazon Forecast dataset.
  - info:
      name: Describe Dataset
      type: http
    http:
      method: GET
      url: https://forecast.{region}.amazonaws.com/describe/dataset/:datasetArn
      params:
      - name: datasetArn
        value: ''
        type: path
        description: ARN of the dataset.
    docs: Describes an Amazon Forecast dataset.
- info:
    name: Dataset Groups
    type: folder
  items:
  - info:
      name: List Dataset Groups
      type: http
    http:
      method: GET
      url: https://forecast.{region}.amazonaws.com/dataset-groups
      params:
      - name: maxResults
        value: ''
        type: query
        description: Maximum results.
      - name: nextToken
        value: ''
        type: query
        description: Pagination token.
    docs: Returns a list of dataset groups.
  - info:
      name: Create Dataset Group
      type: http
    http:
      method: POST
      url: https://forecast.{region}.amazonaws.com/dataset-groups
      body:
        type: json
        data: '{}'
    docs: Creates a dataset group, which holds a collection of related datasets.
- info:
    name: Predictors
    type: folder
  items:
  - info:
      name: List Predictors
      type: http
    http:
      method: GET
      url: https://forecast.{region}.amazonaws.com/predictors
      params:
      - name: maxResults
        value: ''
        type: query
        description: Maximum results.
      - name: nextToken
        value: ''
        type: query
        description: Pagination token.
    docs: Returns a list of predictors.
  - info:
      name: Create Predictor
      type: http
    http:
      method: POST
      url: https://forecast.{region}.amazonaws.com/predictors
      body:
        type: json
        data: '{}'
    docs: Creates an Amazon Forecast predictor (ML model) trained on a dataset group.
- info:
    name: Forecasts
    type: folder
  items:
  - info:
      name: List Forecasts
      type: http
    http:
      method: GET
      url: https://forecast.{region}.amazonaws.com/forecasts
      params:
      - name: maxResults
        value: ''
        type: query
        description: Maximum results.
      - name: nextToken
        value: ''
        type: query
        description: Pagination token.
    docs: Returns a list of forecasts.
  - info:
      name: Create Forecast
      type: http
    http:
      method: POST
      url: https://forecast.{region}.amazonaws.com/forecasts
      body:
        type: json
        data: '{}'
    docs: Creates a forecast for each item in the TARGET_TIME_SERIES dataset.
- info:
    name: Export Jobs
    type: folder
  items:
  - info:
      name: Create Forecast Export Job
      type: http
    http:
      method: POST
      url: https://forecast.{region}.amazonaws.com/forecast-export-jobs
      body:
        type: json
        data: '{}'
    docs: Exports a forecast created by CreateForecast to your Amazon S3 bucket.
- info:
    name: Tags
    type: folder
  items:
  - info:
      name: List Tags For Resource
      type: http
    http:
      method: GET
      url: https://forecast.{region}.amazonaws.com/tags/:resourceArn
      params:
      - name: resourceArn
        value: ''
        type: path
        description: ARN of the resource.
    docs: Lists the tags for an Amazon Forecast resource.
  - info:
      name: Tag Resource
      type: http
    http:
      method: POST
      url: https://forecast.{region}.amazonaws.com/tags/:resourceArn
      params:
      - name: resourceArn
        value: ''
        type: path
        description: ARN of the resource.
      body:
        type: json
        data: '{}'
    docs: Associates the specified tags to a resource.
bundled: true