MULTIPLE MONTE CARLO SIMULATED HIDDEN MARKOV MODEL FOR FUZZY TIME SERIES FORECASTING

This paper presents a Monte Carlo based Hidden Markov Model (HMM) for fuzzy timeseries forecasting. To make the nature of conjecture and randomness of forecasting morerealistic, the Monte Carlo method with different simulation size is adopted to estimate theforecasting outcome. To address the insufficiency in data associated with the HMM model,we adopted a method called smoothing. A number of simulations was performed usingMATLAB simulation environment. The performance of the model was evaluated using thedaily average temperature and cloud density of Taipei, Taiwan. In addition to improvingforecasting accuracy, the proposed model adheres to the central limit theorem, and thus,the result statistically approximates to the real mean of the target value being forecasted.Results showed that the proposed model attain and MSE, RMSE, and AFEP of 0.8596,2.4283, 0.9272 respectively.