• TWO FACTORS TIME VARIANT FUZZY TIME SERIES FORECASTING MODEL BASED ON FUZZY INTERVAL

Abstract

During the last decade different models have been designed and developed. A drawback of traditional forecasting method is that they cannot deal with forecasting problems in which the historical data are linguistic values. To overcome the drawback of the traditional time series, fuzzy time series forecasting is used to forecast. In this paper authors developed and improved fuzzy time series on two factor time variant analysis via considering the latest second factor and previous first factor values and the fuzzy interval. In most of the realistic situation the duplicates of data are significant. The proposed method uses heuristic approach to define multiset based partitions of the universe of discourse and fuzzy interval approach. Two numerical data sets namely Temperature and cloud density is selected to illustrate the proposed method and compare with other time series models.