The Design of a Forecasting Support Models on Demand of Durian for Export Markets by Time Series and ANNs

Nowadays, Durian is the most important exported fruit of Thailand. The export value of durian is approximately 144.87 million USD per year and growing increasingly. The problem in this durian product has been oversupply since the product has been brought out into the market simultaneously; causing durian growers sell their product lower than cost price. In order to avoid the problem of durian exceeds the needs of consumers. Therefore, the objective of this research is to design the forecasting model of the demand of durian in export markets. This research is to find for forecasting demand of four kinds of durian: fresh durian, frozen durian, durian paste and durian chips in the next year. Firstly, applying Output models the four Time Series by Moving Average, Deseasonalised, Exponential Smoothing and Double Exponential Smoothing, secondly, applying Input models: Regression model and Artificial Neural Networks (ANNs) model. The forecast model which has the least value of Mean Absolute Percentage Error (MAPE) is the most accurate forecast model. The results of Output models reveal that the most accurate forecast model is Deseasonalised model which gives the least value of MAPE in three kinds of durian: 1) durian paste at the percentage of 8.66, 2) frozen durian at the percentage of 9.78 and 3) fresh durian at the percentage of 19.24 while Input models reveal that the most accurate forecast model is Artificial Neural Networks (ANNs) model gives the least value of MAPE of durian chips at the percentage of 29.76. After attaining the accurate forecasting model, this is applied with the Linear Programming (LP) model to assess the value of appropriate quantity for domestic and export markets of four kinds of durian for the maximum profit in the following year. The maximum profit quantity of each kinds of durian able to helpful to the durian growers are able to sales planning and processed durian that are the most profitable.

[1]  Steven C. Wheelwright,et al.  Forecasting: Methods and Applications, 3rd Edition , 1998 .

[2]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[3]  Bernard W. Taylor,et al.  Introduction to Management Science , 2006 .

[4]  A. Kengpol,et al.  A Procurement Planning Improvement by Using Linear Programming and Forecasting Models , 2007, PICMET '07 - 2007 Portland International Conference on Management of Engineering & Technology.

[5]  Enriqueta Vercher,et al.  A spreadsheet modeling approach to the Holt-Winters optimal forecasting , 2001, Eur. J. Oper. Res..

[6]  Henry C. Co,et al.  Forecasting Thailand's rice export: Statistical techniques vs. artificial neural networks , 2007, Comput. Ind. Eng..

[7]  Martin T. Hagan,et al.  Neural network design , 1995 .

[8]  M. Qi,et al.  Forecasting Aggregate Retail Sales: a Comparison of Arti"cial Neural Networks and Traditional Methods , 2001 .

[9]  Steven C. Wheelwright,et al.  Forecasting methods and applications. , 1979 .

[10]  C CoHenry,et al.  Forecasting Thailand's rice export , 2007 .

[11]  Raphael R. Bar-On,et al.  Forecasting Tourism Demand: Methods and Strategies , 2003 .

[12]  Hamdy A. Taha,et al.  Operations Research: An Introduction (8th Edition) , 2006 .

[13]  Guoqiang Peter Zhang,et al.  Neural network forecasting for seasonal and trend time series , 2005, Eur. J. Oper. Res..

[14]  Masood A. Badri,et al.  Combining the analytic hierarchy process and goal programming for global facility location-allocation problem , 1999 .

[15]  Douglas C. Frechtling,et al.  Forecasting Tourism Demand: Methods and Strategies , 2001 .

[16]  P. Vlek,et al.  Comparison of adaptive techniques to predict crop yield response under varying soil and land management conditions , 2005 .