Time Variant Fuzzy Time Series Approach for Forecasting Using Particle Swarm Optimization

Fuzzy time series have been developed during the last decade to improve the forecast accuracy. Many algorithms have been applied in this approach of forecasting such as high ordertime invariant fuzzy time series. In this paper, we present a hybrid algorithm to deal with the forecasting problem based ontime variant fuzzy time series and particle swarm optimization algorithm, as a highly efficient and a new evolutionary computation technique inspired by bir·ds ' flight andcommunication behaviors. The proposed algorithm determines the length of each interval in the universe of discourse and degreeof membership values, simultaneously. A numerical data set is selected to illustrate the proposed method and compare the forecasting accuracy with three fuzzy time series methods. The results indicate that the proposed algorithm satisfactorily competes well with similar approaches

کلیدواژه ها:

Forecasting ، Fuzzy time series ، Time variant ، Particle Swarm Optimization