Determination of fuzzy relations for economic fuzzy time series models by neural networks

Abstract

Based on the works /11, 22, 27/ a fuzzy time series model is proposed and applied to predict chaotic financial process. Thwe general methodological framework of classical and fuzzy modelling of economic time series is considered. A complete fuzzy time series modellling approach is proposed which includes: determining and developing of fuzzy time series models, developing and calculating of fuzzy relations among the observations, calculating and interpreting the outputs. To generate fuzzy rules from data, the neural network with SCL-based product-space clustering is used.