Finding the best smoothing coefficient for the unary exponential smoothing method using the nonlinear programming method

Abstract

The unilateral exponential smoothing method is used in the prediction process, and this method requires estimating the specific parameters that represent the unequal weights that are given to the previous observations. Its optimal values are obtained by minimizing the mean square error (MSE).
In this research, the nonlinear programming method was used to determine the best smoothing coefficient, that is, the best value of ( ) that gives the least ((MSE) and leads to the best prediction process. More than one model was solved using nonlinear programming with the help of the ready-made software (Win QSB), and from The results show the effectiveness of using this method in finding the smoothing coefficient.