Determination the smoothing constant that minimizes mean absolute error and mean square deviation

Mamat, M. and Prabowo, A. and Tripena, A. and Pratama, D.A. and Susilo, I.G. and Mukarromah, Z. and Sukono, . and Bon, A.T. (2021) Determination the smoothing constant that minimizes mean absolute error and mean square deviation. In: 11th Annual International Conference on Industrial Engineering and Operations Management, 07-11 Mac 2021, Virtual, Online.

Text FH03-FIK-21-56567.pdf Restricted to Registered users only Download (215kB)

Abstract

Exponential smoothing technique has become one of the quantitative techniques are very important in forecasting. The accuracy of forecasting based on this method depends on a parameter called the smoothing constant. Selection of smoothing constant value becomes very crucial because in forecasting prosecuted forecasting error is minimal. This paper discusses the selection of the optimal smoothing constant value which minimizes the mean square error (MSE) and the mean absolute deviation (MAD). Trial and error method is used to determine the optimal value of the smoothing constant based on the two criterias (MSE and MAD). Based on the analysis carried out, there was no regularity of the relationship between the amount of data and the smoothing constant value that minimized MAD and MSE.

Actions (login required)

View Item