The Generalized Fuzzy Time Series Model for Forecasting Base on the Optimization of the Length of Intervals

Abstract:

Based on the analysis of some conventional fuzzy time series model,this paper proposes a new method by using a single constrained optimization to determine the interval length for improving the forecasts.The conventional fuzzy time series models are enhanced by forecast-weighted method in the forecasting.In the proposed model,which is evaluated by mean square error(MSE),fuzzy membership degrees are used to calculate forecast weights. The empirical results show that the proposed model outperforms than the conventional models.

• Periodical: Applied Mechanics and Materials (Volume 596)
• Pages: 286-291
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.596.286
• Online since: July 2014
• Authors: Yan Hong Wang, Wang Ren Qiu
• Keywords: Forecasting Model, Fuzzy Time Series, Partition of Interval

References

[1] Q. Song and B.S. Chissom. Fuzzy Set and Systems 54(1993),P. 269-277.

[2] Q. Song and B.S. Chissom. Fuzzy Set and Systems 54(1993),P. 1-10.

[3] Q. Song and B.S. Chissom. Fuzzy Set and Systems 62(1994),P. 1-8.

[4] Chen S M. Fuzzy Set and Systems , 1996, 81(3),P. 311-319.

[5] Lee M H, Efendi R, Ismail z. Matematika, 2009, 25(1),P. 67-78.

[6] K. Huarng. Fuzzy Set and Systems 123(2001), pp.387-394.

[7] J. Kiefer. Proceeding of the American Mathematical Society 4(1953),P. 502-506.

[8] R.P. Brent. Prentice-Hall, EngleW-ood Cliffs, New Jersey, (1973).

[9] G.E. Forsythe M.A. Malcolm and C.B. Moler. Prentice Hall, New Jersey, (1976).

[10] Chen S.M. (2002). Cybernetics and Systems, 33, P. 1-16.

[11] Huarng K.H. (2001). Fuzzy Sets and Systems, 123(3), P. 387-394.

[12] Aladag C.H., Basaran M.A., Egrioglu E., Yolcu U, Uslu V.R. (2009). Expert Systems with Applications, 36, P. 4228-4231.

DOI: 10.1016/j.eswa.2008.04.001