- Function forecasting::ExponentialSmoothingTune(dataValues, noObservations, alpha, alphaLow, alphaUpp)
forecasting::ExponentialSmoothingTune
The forecasting::ExponentialSmoothingTune()
procedure is a time series
forecasting helper procedure of forecasting::ExponentialSmoothing()
by computing the
\(\alpha\) for which the mean squared error is minimized.
Function Prototype
forecasting::ExponentialSmoothingTune(
! Provides the alpha for which the mean squared error is minimized.
dataValues, ! Input, parameter indexed over time set
noObservations, ! Scalar input, length history
alpha, ! Scalar output, weight of observation
! that minimizes mean squared error
alphaLow, ! Optional input, default 0.01
alphaUpp) ! Optional input, default 0.99
Arguments
- dataValues
A one dimensional parameter containing the observations for the first \(T\) elements of the time set.
- noObservations
Specifies the number of elements that belong to the history of the time set. This parameter corresponds to \(T\) in the notation presented in Time Series Forecasting Notation.
- alpha
Upon return it provides the weighting factor \(\alpha\) for which the mean squared error is minimized when using
forecasting::ExponentialSmoothing()
on the samedataValues
.- alphaLow
Lowerbound on \(\alpha\), default 0.01.
- alphaUpp
Upperbound on \(\alpha\), default 0.99.
Note
In order to use this function, the Forecasting
system library needs
to be added to the application.
Please note that this function performs an optimization step; a nonlinear programming solver should be available and, in an AIMMS PRO environment, it should be run server side.
Example
To further understand about this procedure and library, please use the Demand Forecasting example.