Generalized Fuzzy Time Series Forecasting Model Enhanced with Particle Swarm Optimization

In the past two decades, many forecasting models based on the concepts of fuzzy time series have been proposed for dealing with various problem domains. In this paper, we present a novel model to forecast enrollments and the close prices of stock based on particle swarm optimization and generalized fuzzy logical relationships. After that some concepts of the generalized fuzzy logical relationships and an operation for combining the generalizedrelationships are introduced in the first part of this paper, we use particle swarm optimization to optimal represents for the given intervals in the universe of discourse to increase the forecasting accuracy. To test the effectiveness of the model, the proposed method is demonstrated on the procedure of forecasting enrollments as well as its experiment on forecasting the close price of Shanghai Stock Exchange Composite Index. Empirical analyses show that theproposed method gets a higher average forecasting accuracy rate than the existing methods.