Selecting exponential smoothing constants: an application of pattern search

Publisher Website
Google Scholar
Abstract
Exponential smoothing is one means of preparing short-term sales forecasts on a routine basis. To use exponential smoothing, however, one must decide the proper values for the smoothing constants in the forecasting model. One method for selecting the smoothing constants involves conducting a grid search to evaluate a wide range of possible values. An alternative method, called pattern search, is presented in this paper and is compared to the grid search procedure. Two criteria are used in comparing these procedures: (1) the standard deviation of the forecast error, and (2) the computing time necessary for a solution, The results of this comparison indicate that, when the exponential smoothing model includes trend and seasonal adjustments, pattern search requires far less computer time than the grid search procedure to produce smoothing constant values for which the forecast error values are comparable.

This publication has 6 references indexed in Scilit: