Building Fuzzy Random Autoregression Model and Its Application

Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 15)


The purpose of economic analysis is to interpret the history, present and future economic situation based on analyzing economical time series data. The autoregression model is widely used in economic analysis to predict an output of an index based on the previous outputs. However, in real-world economic analysis, given the co-existence of stochastic and fuzzy uncertainty, it is better to employ a fuzzy system approach to the analysis. To address regression problems with such hybridly uncertain data, fuzzy random data are introduced to build the autoregression model. In this paper, a fuzzy random autoregression model is introduced and to solve the problem, we resort to some heuristic solution based on σ-confidence intervals. Finally, a numerical example of Shanghai Composite Index is provided.


fuzzy autoregression model fuzzy random data fuzzy random autoregression model time series data confidence interval 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Yabuuchi, Y., Watada, J., Toyoura, Y.: Fuzzy AR model of stock price. Scientiae Mathematicae Japonicae 60(2), 303–310 (2004)MathSciNetMATHGoogle Scholar
  2. 2.
    Zadeh, L.A.: Fuzzy sets. Information and Control 8(3), 338–353 (1965)MathSciNetMATHCrossRefGoogle Scholar
  3. 3.
    Ozawa, K., Watanabe, T., Kanke, M.: Forecasting Fuzzy Time Series with Fuzzy AR Model. In: Proceedings, the 20th International Conference on Computers & Industrial Engineering, pp. 105–108 (1996)Google Scholar
  4. 4.
    Kwakernaak, H.: Fuzzy random variables-I. Definitions and Theorems. Information Sciences 15(1), 1–29 (1978)MathSciNetMATHCrossRefGoogle Scholar
  5. 5.
    Hop, N.V.: Fuzzy stochastic goal programming problems. European Journal of Operational Research 176(1), 77–86 (2007)MathSciNetMATHCrossRefGoogle Scholar
  6. 6.
    Wang, G., Qiao, Z.: Linear programming with fuzzy random variable coefficients. Fuzzy Sets and Systems 57(3), 295–311 (1993)MathSciNetMATHCrossRefGoogle Scholar
  7. 7.
    Wang, S., Watada, J.: Reliability optimization of a series-parallel system withfuzzy random lifetimes. International Journal of Innovative Computing, Information & Control 5(6), 1547–1558 (2009)Google Scholar
  8. 8.
    Nahmias, S.: Fuzzy variables. Fuzzy Sets Syst. 1(2), 97–111 (1978)MathSciNetMATHCrossRefGoogle Scholar
  9. 9.
    Liu, B., Liu, Y.K.: Expected value of fuzzy variable and fuzzy expected value models. IEEE Trans. Fuzzy Syst. 10(4), 445–450 (2002)CrossRefGoogle Scholar
  10. 10.
    Liu, Y.K., Liu, B.: Fuzzy random variable: A scalar expected value operator. Fuzzy Optim. Decision Making 2(2), 143–160 (2003)CrossRefGoogle Scholar
  11. 11.
    Watada, J., Pedrycz, W.: A fuzzy regression approach to acquisition of linguistic rules. In: Pedrycz, W., Skowron, A., Kreinovich, V. (eds.) Handbook on Granular Comutation, ch. 32, pp. 719–740. John Wiley & Sons Ltd., Chichester (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Lu Shao
    • 1
  • You-Hsi Tsai
    • 1
  • Junzo Watada
    • 1
  • Shuming Wang
    • 1
  1. 1.Graduate School of Information, Production and SystemsWaseda UniversityWakamatsuJapan

Personalised recommendations