R.R. RZAYEV, H.M. SHIHALIYEVA
ONE APPROACH TO DEFUZZIFICATION OF THE OUTPUTS OF FUZZY TIME SERIES MODELS
By the specific example of the time series of "Marginality of sales" indicator, the authors consider known fuzzy forecasting models that differ in rules of fuzzification and/or defuzzification. In the context of this study, this paper presents a new approach to defuzzification of the outputs of fuzzy time series models on the base of applying the fuzzy set point-estimation method. As compared with some well-known defuzzification rules, the proposed method improves the statistical quality of time series forecasting.
Keywords: time series, fuzzy set, fuzzy predict, fuzzy relationship, point estimate
ONE APPROACH TO DEFUZZIFICATION OF THE OUTPUTS OF FUZZY TIME SERIES MODELS
By the specific example of the time series of "Marginality of sales" indicator, the authors consider known fuzzy forecasting models that differ in rules of fuzzification and/or defuzzification. In the context of this study, this paper presents a new approach to defuzzification of the outputs of fuzzy time series models on the base of applying the fuzzy set point-estimation method. As compared with some well-known defuzzification rules, the proposed method improves the statistical quality of time series forecasting.
Keywords: time series, fuzzy set, fuzzy predict, fuzzy relationship, point estimate