MODELING OF CAPACITY UTILIZATION RATIO WITH FUZZY TIME SERIES BASED ON MARKOV TRANSITION MATRIX

Year 2015, Volume: 64 Issue: 2, 63 - 75, 01.08.2015

Hilal Güney Akif M. Bakır

https://doi.org/10.1501/Commua1_0000000734

Abstract

Modeling of time series with fuzzy logic has found an increasingly expanding usage in recent years. One of the most important reasons for thisis that fuzzy logic approach doesn’t require assumptions needed by the typical time series. Inclusion of the some weightings and probability calculations at the forecast stage into the first studies starting through the modeling of time series with fuzzy logic resulted in further improvement of the forecast quality. Tsaur(2011) achieved better forecasted results by including the Markov transition probabilities matrix. Fuzzy time series is also an approach which can be *exibly used in various model structures as it easily overcomes the difficulties causedby the model structure - linear or non-linear form. In this study, Markov method of Tsaur is applied on the monthly capacity utilization ratio (CUR)of Turkey which has a non-linear structure and free of seasonality belongingto the period between 2007-2015. In this sense, the results are compared to the results of SETAR model and it’s seen that Tsaur’s approach has provided better results compared to the forecasts of typical time series

References

• Alada¼g, Ç., H., Türk¸sen, I., B.(2015)’A Novel Membership Value Based Performance Mea- sure,’ Journal of Intelligent and Fuzzy Systems, 28(2): 919-928.
• Alada¼g, Ç. H., Ba¸saran,M. A. ,E¼grio¼glu, E. , Yolcu, U. and Uslu, V. R.(2009)‘Forecasting in High Order Fuzzy Time Series by Using Neural Networks to De…ne Fuzzy Relations’, Expert Systems with Applications, 36:4228-4231.
• Alada¼g, Ç., H., Yolcu, U, E¼grio¼glu, E., (2010) ‘A High Order Fuzzy Time Series Forecasting Model Based on Adaptive Expectation and Arti…cial Neural Networks’, Mathematica and Computers in Simulation, 81:875-882.
• Chen, S.M.(1996) ‘Forecasting Enrollments Based on Fuzzy Time Series’, Fuzzy Sets and Systems, 81:311-319.
• Hwang, J., R., Chen, S., M., Lee, C., H.(1998) ‘Handling Forecasting Problems Using Fuzzy Time Series’, Fuzzy Sets and Systems, 100:217-228.
• Song, Q. , Chissom, B.S.,(1991) ‘Forecasting Enrollments with Fuzzy Time Series Part 1’, Fuzzy Sets and Systems, 54:1-10.
• Song, Q. , Chissom, B.S.,(1993) ‘Fuzzy Time Series and its Models’, Fuzzy Sets and Systems, 54: 269-.
• Tsaur, R., C.(2011) ‘A Fuzzy Time Series-Markov Chain Model with an Application to Fore- cast the Exchange Rate Between the Taiwan and US Dolar’, International Journal of Innov- ative Computing, Information and Control, 8:1349-4198.
• Yu, H., K.(2005-a)‘Weighted Fuzzy Time Series Models for TAIEX Forecasting”, Physica A, 349:609-624.
• Yu, H., K. (2005-b)‘A Re…ned Fuzzy Time Series Model for Forecasting’, Physica A, 346:657- 681.
• Zadeh, L.A.,(1965 ) ‘Fuzzy Sets’, Information and Control, 8:338-353. Address : Hilal GÜNEY, Gazi University, Department of Statistics, Besevler ANKARA E-mail : [e-mail] Address : M.Akif BAKIR, Gazi University, Department of Statistics, Besevler ANKARA. E-mail : [e-mail]