Fuzzy time series forecasting model using combined models

Since nineteenth century, many researchers proposed various methods for forecasting enrollments, temperature prediction, stock price etc. In this paper a new model is introduced to forecast the fuzzy time series. By using Markov chain model the adjusted forecasted values are obtained and with aggregated fuzzy relationship the forecasted values are obtained. Using these two values, the proposed method is used to improve the accuracy. By giving example, forecasting the fuzzy time series are explained. The University of Alabama is used for illustration. Finally error analysis is made and error percentage is calculated and compared with existing methods. The proposed model confirms the potential benifits of the proposed approach with very small AFER.