A New Latex Price Forecasting Model to Reduce the Risk of Rubber Overproduction in Thailand

  • Jitian Xiao
  • Panida Subsorn
Part of the Intelligent Systems Reference Library book series (ISRL, volume 33)


One of the key areas in risk management in the public rubber industry in Thailand (PARIT) is to accurately forecast rubber latex prices thus to adjust rubber production in a timely manner. Accurately forecasting rubber latex price may not only reduce risks of overproduction and costs of over stocking, but also respond promptly and directly to global market thus improve in gaining higher sales in the competitive rubber marketing environment. This chapter presents a rubber latex price forecasting model, with three variations, i.e., one-year prediction, 6-month prediction and 4-month prediction, each embedding with either non-neural or neural network training techniques. The model is validated using actual rubber latex prices trend data, which in turn compared with experimental forecasting results to determine forecasting accuracy and the best-fitting model for policy makers in PARIT.


Risk management latex price forecast neural network training techniques 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Center of Agricultural Information, Crop forecasting in Thailand, C.o.A. Information. The Office of Agricultural Economics, OAE, Bangkok (2002)Google Scholar
  2. 2.
    Center of Agricultural Information, Agricultural prices information management, Center of Agricultural Information. The Office of Agricultural Economic, OAE, Bangkok (2009)Google Scholar
  3. 3.
    Chiulli, R.M.: Quantitative analysis: An introduction Automation and Production Systems. In: Methodologies and Applications. CRC Press, Singapore (1999)Google Scholar
  4. 4.
    Co, H.C.: Forecasting Thailand’s rice export: Statistical techniques vs. artificial neural networks. Computers & Industrial Engineering 53, 1140–1154 (2007)CrossRefGoogle Scholar
  5. 5.
    Crowther, P.S., Cox, R.J.: A Method for Optimal Division of Data Sets for Use in Neural Networks. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds.) KES 2005. LNCS (LNAI), vol. 3684, pp. 1–7. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  6. 6.
    Dana, J., Gilbert, C.L.: Managing Agricultural Price Risk in Developing Countries. In: Geman, H. (ed.) Risk Management in Commodity Markets: from Shipping to agricultural and Energy, pp. 207–237. John Wiley & Sons, Ltd. (2008)Google Scholar
  7. 7.
    Fausett, L.: Fundamentals of neural networks: architectures, algo-rithms, and application. Prentice-Hall, USA (1994)Google Scholar
  8. 8.
    Funahashi, K.: On the approximate realization of continuous mappings by neural networks. Neural Networks 2, 183–192 (1989)CrossRefGoogle Scholar
  9. 9.
    Geurts, M., Lawrence, K.D., Guerard, J.: Forecasting sales. JAI PRESS INC., Greenwich (1994)Google Scholar
  10. 10.
    Hodge, L., Mothersole, J.: Pricing Risks – Be prepared for the Next Round of Commodity Price Swing. In: 95th ISM Annual International Supply Management Conference (April 2010)Google Scholar
  11. 11.
    Leechawengwong, M., Prathummintra, S., Thamsiri, Y.: The Devel-opment of Basic Rubber Database. Rubber Research Institute of Thailand, Bangkok (2002)Google Scholar
  12. 12.
    Markland, R.E., Sweigart, J.R.: Quantitative methods: Applications to managerial decision making. John Wiley & Sons Inc., Canada (1987)Google Scholar
  13. 13.
    Mentzer, J.T., Moon, M.A.: Sales forecasting management: A de-mand management approach, 2nd edn. SAGE Publications, California (2005)Google Scholar
  14. 14.
    Negnevitsky, M.: Artificial intelligence: a guide to intelligent systems, 2nd edn. Addison-Wesley, New York (2005)Google Scholar
  15. 15.
    Office of Industrial Economics & Economic Research and Training Center. In: Study of Industrial Structure for Enhancing Competitiveness of Rubber Product Industries. Ministry of Industry, Bangkok (1998)Google Scholar
  16. 16.
    Olson, D.L., Courtney, J.F.: Decision support models and expert systems. Macmillan Publishing Company, New York (1992)Google Scholar
  17. 17.
    The Rubber Economist Ltd Risk Management in the Rubber Industry (2010), (searched on November 20, 2010)
  18. 18.
    Rubber Research Institute of Thailand (1997); Academic rubber information. Rubber Research Institute of Thailand, Bangkok (2007)Google Scholar
  19. 19.
    Sangpong, S., Chaveesuk, R.: Time series analysis techniques for forecasting pineapple yield in various sizes. In: Open image in new window (2007)Google Scholar
  20. 20.
    Soyhan, H.S., Kilic, M.E., Gokalp, B., Taymaz, I.: Performance comparison of MATLAB and neuro solution software on estimation of fuel economy by using artificial neural network. In: The Second International Conference ”Intelligent Information and Engineering Systems” (INFOS 2009), Varna, Bulgaria, pp. 71–76 (2009)Google Scholar
  21. 21.
    SPSS Inc. TSMODEL algorithms, Statistical Package for the Social Sciences (2009) Google Scholar
  22. 22.
    SPSS Inc. Introduction to neural networks. Statistical Package for the Social Sciences (SPSS) (2009-1)Google Scholar
  23. 23.
    SPSS Inc. MLP algorithms. Statistical Package for the Social Sciences (2009-2)Google Scholar
  24. 24.
    Subsorn, P.: Enhancing rubber forecasting: The case of the Thai rub-ber industry. In: The Ninth Postgraduate Electrical Engineering & Computing Symposium (PEECS 2008). The University of Western Australia, Perth (2008)Google Scholar
  25. 25.
    Tomita, Y.: Introduction to forecasting, (retrieved January 8, 2008)
  26. 26.
    Twomey, J.M., Smith, A.E.: Validation and verification. In: Artificial Neural Networks for Civil Engineers: Fundamentals and Applications. ASCE Press, New York (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Jitian Xiao
    • 1
  • Panida Subsorn
    • 1
    • 2
  1. 1.School of Computer and Security ScienceEdith Cowan UniversityMt LawleyAustralia
  2. 2.Suan Dusit Rajabhat UniversityBangkokThailand

Personalised recommendations