Exchange rate forecasting by neuro-fuzzy techniques

Modelling the human behaviour in the market of the exchange rate has always been an important challenge for the researchers. Apart from the traditional methods used in forecasting short-term foreign exchange rates, during the last years many researchers started to use soft computing techniques in order to achieve better results. In this paper a neuro-fuzzy model is presented. The model is trained by the training data and, then, the testing data are used for model validation. The model uses time series data of daily quotes of the euro/dollar exchange rate. Root mean square error and other statistical measures are used to evaluate the model performance. Additionally a comparison with conventional forecasting methods is employed.