A higher-order fuzzy neural network for modeling financial time series

This work investigates on the widespread use of fuzzy neural networks in time series forecasting, concerning in particular the energy commodity markets. We propose a new learning strategy suited to any neural model. The proposed approach is further assessed in the case of higher-order Sugeno-type fuzzy rules, which are able to replicate the daily data and to reproduce the same statistical features for various Commodity time series. The data used are obtained from the daily return series of specific energy commodities, such as coal, natural gas, crude oil and electricity, over the period 2001-2010 for both the European and US markets. We will prove that our approach can obtain interesting results in terms of prediction accuracy and volatility estimation, compared to well-known neural and fuzzy neural models and to the ARMA-GARCH statistical paradigm.