Skip to content

/AWS1/CL_FCSEVALPARAMETERS

Parameters that define how to split a dataset into training data and testing data, and the number of iterations to perform. These parameters are specified in the predefined algorithms but you can override them in the CreatePredictor request.

CONSTRUCTOR

IMPORTING

Optional arguments:

IV_NUMBEROFBACKTESTWINDOWS TYPE /AWS1/FCSINTEGER /AWS1/FCSINTEGER

The number of times to split the input data. The default is 1. Valid values are 1 through 5.

IV_BACKTESTWINDOWOFFSET TYPE /AWS1/FCSINTEGER /AWS1/FCSINTEGER

The point from the end of the dataset where you want to split the data for model training and testing (evaluation). Specify the value as the number of data points. The default is the value of the forecast horizon. BackTestWindowOffset can be used to mimic a past virtual forecast start date. This value must be greater than or equal to the forecast horizon and less than half of the TARGET_TIME_SERIES dataset length.

ForecastHorizon <= BackTestWindowOffset < 1/2 * TARGET_TIME_SERIES dataset length

Queryable Attributes

NumberOfBacktestWindows

The number of times to split the input data. The default is 1. Valid values are 1 through 5.

Accessible with the following methods

Method Description
GET_NUMBEROFBACKTESTWINDOWS() Getter for NUMBEROFBACKTESTWINDOWS, with configurable defaul
ASK_NUMBEROFBACKTESTWINDOWS() Getter for NUMBEROFBACKTESTWINDOWS w/ exceptions if field ha
HAS_NUMBEROFBACKTESTWINDOWS() Determine if NUMBEROFBACKTESTWINDOWS has a value

BackTestWindowOffset

The point from the end of the dataset where you want to split the data for model training and testing (evaluation). Specify the value as the number of data points. The default is the value of the forecast horizon. BackTestWindowOffset can be used to mimic a past virtual forecast start date. This value must be greater than or equal to the forecast horizon and less than half of the TARGET_TIME_SERIES dataset length.

ForecastHorizon <= BackTestWindowOffset < 1/2 * TARGET_TIME_SERIES dataset length

Accessible with the following methods

Method Description
GET_BACKTESTWINDOWOFFSET() Getter for BACKTESTWINDOWOFFSET, with configurable default
ASK_BACKTESTWINDOWOFFSET() Getter for BACKTESTWINDOWOFFSET w/ exceptions if field has n
HAS_BACKTESTWINDOWOFFSET() Determine if BACKTESTWINDOWOFFSET has a value