Skip to content

Create What If Analysis

forecastservice_create_what_if_analysis R Documentation

What-if analysis is a scenario modeling technique where you make a hypothetical change to a time series and compare the forecasts generated by these changes against the baseline, unchanged time series

Description

What-if analysis is a scenario modeling technique where you make a hypothetical change to a time series and compare the forecasts generated by these changes against the baseline, unchanged time series. It is important to remember that the purpose of a what-if analysis is to understand how a forecast can change given different modifications to the baseline time series.

For example, imagine you are a clothing retailer who is considering an end of season sale to clear space for new styles. After creating a baseline forecast, you can use a what-if analysis to investigate how different sales tactics might affect your goals.

You could create a scenario where everything is given a 25% markdown, and another where everything is given a fixed dollar markdown. You could create a scenario where the sale lasts for one week and another where the sale lasts for one month. With a what-if analysis, you can compare many different scenarios against each other.

Note that a what-if analysis is meant to display what the forecasting model has learned and how it will behave in the scenarios that you are evaluating. Do not blindly use the results of the what-if analysis to make business decisions. For instance, forecasts might not be accurate for novel scenarios where there is no reference available to determine whether a forecast is good.

The TimeSeriesSelector object defines the items that you want in the what-if analysis.

Usage

forecastservice_create_what_if_analysis(WhatIfAnalysisName, ForecastArn,
  TimeSeriesSelector, Tags)

Arguments

WhatIfAnalysisName

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

ForecastArn

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

TimeSeriesSelector

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

Tags

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

Value

A list with the following syntax: 

list(
  WhatIfAnalysisArn = "string"
)

Request syntax

svc$create_what_if_analysis(
  WhatIfAnalysisName = "string",
  ForecastArn = "string",
  TimeSeriesSelector = list(
    TimeSeriesIdentifiers = list(
      DataSource = list(
        S3Config = list(
          Path = "string",
          RoleArn = "string",
          KMSKeyArn = "string"
        )
      ),
      Schema = list(
        Attributes = list(
          list(
            AttributeName = "string",
            AttributeType = "string"|"integer"|"float"|"timestamp"|"geolocation"
          )
        )
      ),
      Format = "string"
    )
  ),
  Tags = list(
    list(
      Key = "string",
      Value = "string"
    )
  )
)