Analysis of Japanese national consumer price index using fuzzy autocorrelation model with fuzzy confidence intervals

Management systems and economic systems are complex because they involve human behaviors and are affected by many factors. When a system includes uncertainty such as those concerning human behaviors, a fuzzy system approach plays a pivotal role in its analysis. Therefore, many results concerning their work have been reported. Yabuuchi et al. have proposed a fuzzy autocorrelation model which uses the concept of soft computing for the Box-Jenkins model. Moreover, fuzzy random variables have been used for the fuzzy autocorrelation model and a predictive accuracy of the model improved. In this work, an improved fuzzy autocorrelation model by using fuzzy random variables will be compared with a fuzzy autocorrelation model by Japanese national consumer price index. And we will be confirmed the proposed model can be with high accuracy.