An improvement in forecasting interval based fuzzy time series

In this paper, we have proposed a fuzzy interval time series model using a new strategy to replace the conventional defuzzification step, where genetic algorithm has been used to optimize the interval parameters and neural network has been used to learn the trend of the time series. First order fuzzy time series with equal time interval has been used on two data sets, enrollments of the University of Alabama and gold exchange traded fund. We compare the proposed model with two other existing models. The results of the comparisons show that the proposed model performs better.