การคัดเลือกตัวแบบพยากรณ์ราคามะม่วงเขียวเสวย (SELECTION OF FORECASTING MODELS FOR THE MANGO PRICES )

Abstract

                   The objective of this study was to select the appropriate forecasting model for the mango prices. The data gathered from the website of the Office of Agricultural Economics during January 2005 to March 2018 of 159 values were used and divided into 2 sets. The first set had 147 values from January 2005 to March 2017 for constructing the forecasting models by Box-Jenkins method, simple seasonal exponential smoothing method, Winters’ additive exponential smoothing method, Winters’ multiplicative exponential smoothing method, and combined forecasting method that included two forecasting methods with a low mean absolute percentage error (MAPE). The second set had 12 values from April 2017 to March 2018 for comparing the accuracy of the forecasts via the criterion of the lowest MAPE. Research findings indicated that for all forecasting methods that had been studied, the most accurate method was Box-Jenkins method