Fuzzy Autoregressive Model using Real Time Series Data

Abstract

An autocorrelated fuzzy time series model is an autoregressive model fuzzified by the author. This model uses fuzzy time series data and gives fuzzy outputs. In addition, although its prediction accuracy is good, the coefficients of the model can only be obtained by solving the two LP problems. Real time series data are easier to obtain than fuzzy time series data. Therefore, a fuzzy time series model using real time series data is proposed. The proposed model was applied to numerical examples and good results were obtained. The challenge of improving the width of the model was found, and this paper reports the results.