Forecasting Exchange Rates: A Neuro-Fuzzy Approach

Abstract

This paper presents an adaptive neuro-fuzzy inference system (ANFIS) for USD/JPY exchange rates forecasting. Previous work often used time series techniques and neural networks (NN). ANFIS can be used to better explain solutions to users than completely black-box models, such as NN. The proposed neuro-fuzzy rule based system applies some technical and fundamental indexes as input variables. In order to generate membership functions (MFs), we make use of fuzzy clustering of the output space. The neuro-fuzzy model is tested with 28 candidate input variables for both currencies. For the purpose of comparison, Sugeno-Yasukawa model, feedforward multi-layer neural network, and multiple regression are benchmarked. The comparison demonstrates that the presented algorithm shows its superiority in terms of prediction error minimization, robustness and flexibility