Comparison of Exponential Smoothing Methods in Forecasting Palm Oil Real Production

International Conference on Computing and Applied Informatics 2016

物理学;计算机科学

Siregar, B.^1 ; Butar-Butar, I.A.^1 ; Rahmat, R.F.^1 ; Andayani, U.^1 ; Fahmi, F.^2

Dept. of Information and Technology, Faculty of Computer Science and Information Technology, University of Sumatera Utara, Jl. Dr. Mansur 9, Medan Indonesia, Indonesia^1

Dept. of Electrical Engg, Faculty of Engineering, University of Sumatera Utara, Jl. Dr. Mansur 9, Medan Indonesia, Indonesia^2

关键词: Double exponential;    Exponential smoothing;    Exponential smoothing method;    Forecasting models;    Oil production;    Production data;    Root mean squared;    Strategic management;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/801/1/012004/pdf
DOI  :  10.1088/1742-6596/801/1/012004

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

Palm oil has important role for the plantation subsector. Forecasting of the real palm oil production in certain period is needed by plantation companies to maintain their strategic management. This study compared several methods based on exponential smoothing (ES) technique such as single ES, double exponential smoothing holt, triple exponential smoothing, triple exponential smoothing additive and multiplicative to predict the palm oil production. We examined the accuracy of forecasting models of production data and analyzed the characteristics of the models. Programming language R was used with selected constants for double ES (α and β) and triple ES (α, β, and γ) evaluated by the technique of minimizing the root mean squared prediction error (RMSE). Our result showed that triple ES additives had lowest error rate compared to the other models with RMSE of 0.10 with a combination of parameters α = 0.6, β = 0.02, and γ = 0.02.