|
Study of Several Exponential Smoothing Methods for Forecasting Crude Palm Oil Productions in Thailand |
|---|---|
| รหัสดีโอไอ | |
| Creator | Apidet Booranawong4 |
| Title | Study of Several Exponential Smoothing Methods for Forecasting Crude Palm Oil Productions in Thailand |
| Contributor | Kittiphoom Suppalakpanya, Ruamporn Nikhom and Thitima Booranawong |
| Publisher | King Mongkut's Institute of Technology Ladkrabang |
| Publication Year | 2562 |
| Journal Title | Current Applied Science and Technology |
| Journal Vol. | 19 |
| Journal No. | 2 |
| Page no. | 123-139 |
| Keyword | exponential smoothing methods, forecasting, crude palm oil productions, Thailand |
| URL Website | https://www.tci-thaijo.org/index.php/cast |
| Website title | https://www.tci-thaijo.org/index.php |
| ISSN | 2586-9396 |
| Abstract | In this paper, a study of several exponential smoothing methods for forecasting crude palm oil productions in Thailand during January 2018 to March 2018 is presented. The exponential smoothing methods include the Double Exponential Smoothing (DES) method, the Multiplicative Holts-Winters (MHW) method, the Additive Holt-Winters (AHW) method, the Improved Additive Holts-Winters (IAHW) method, and the Extended Additive Holts-Winters (EAHW) method. The input data from January 2006 to December 2017 are collected from the database of the Department of Internal Trade, Ministry of Commerce, Thailand. The major contributions of our paper are twofold. First, the well-known exponential smoothing methods (i.e. the DES, the MHW, and the AHW methods) and the recent methods proposed in the literature (i.e. the IAHW and the EAHW methods) are tested and evaluated. Here, the best forecast results by optimal solutions are determined. Second, different sets of input data including 3-year data (2015-2017), 6-year data (2012-2017), 9-year data (2009-2017), and 12-year data (2006-2017) are used as the inputs for all forecasting methods. Here, how the different sets of input data affect forecasting accuracy are revealed. Our study demonstrates that the traditional AHW and the recently proposed EAHW methods provide the smallest forecasting error measured by Mean Absolute Percentage Error (MAPE) in forecasting crude palm oil productions. The study also indicates that both the AHW and the EAHW methods significantly show accurate forecast results when 12-year input data are applied. Forecast results of January 2018 to March 2018 and the trends of the average monthly and yearly palm oil productions are also reported. We believe that the research methodology and results presented in this work can be useful for strategy setting of the Thai agriculturist and government. |
