The Logarithm Function with a Fuzzy Time Series

The fuzzy time series has recently received increasing attention because of its capability in dealing with vague and incomplete data. This article presents an improved fuzzy time series model; we show that our method is as complete as the original definition but with higher reliability (Chou and Lee). Experimental results using the University of Alabama’s enrollment data (adapted by Song and Chissom) demonstrate that the proposed forecasting model outperforms the existing model (Lee and Chou) in terms of accuracy and robustness. Moreover, the forecasting model adheres to the consistency principle that the logarithm function with the fuzzy time series leads to more accurate results.