TAIEX Forecasting Based on Fuzzy Time Series and the Automatically Generated Weights of Defuzzified Forecasted Fuzzy Variations of Multiple-Factors

Abstract

This paper presents a new method to forecast the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) based on fuzzy time series and the automatic generated weights of defuzzified forecasted fuzzy variations of multiple-factors. The proposed method uses the variation magnitude of adjacent historical data to generate fuzzy variation groups of the main factor (i.e., the TAIEX) and the elementary secondary factors (i.e., the Dow Jones, the NASDAQ and the M1B), respectively. Based on the variation magnitudes of the main factor TAIEX and the elementary secondary factors of a particular trading day, it gets the forecasted variation of the TAIEX of the next trading day forecasted by each factor. Based on the correlation coefficients between the forecasted fuzzy variation of the main factor and the forecasted fuzzy variation of each elementary secondary factor, it automatically generates the weights of the defuzzified forecasted fuzzy variation of the main factor and the defuzzified forecasted fuzzy variation of each elementary secondary factor, respectively. Based on the closing index of the TAIEX of the trading day and the weighted forecasted variation, it generates the final forecasted value of the next trading day. The experimental results show that the proposed method gets higher average forecasting accuracy rates than the existing methods.KeywordsElementary Secondary FactorsForecasted Fuzzy VariationsFuzzy Time SeriesFuzzy Variation GroupsMain FactorSecondary FactorsTAIEXVariation MagnitudeCorrelation Coefficients