A New Approach for Handling Forecasting Problems Using High-Order Fuzzy Time Series

In recent years, some researchers used high-order fuzzy time series to deal with forecasting problems. In this paper, we present a new method for forecasting the enrollments of the University of Alabama based on the high-order fuzzy time series. The proposed method uses the socalled “second order differences” of the enrollments of the previous years to determine the trend of the forecasting. The proposed method gets a higher forecasting accuracy rate than the existing methods.