Extracting input features and fuzzy rules for forecasting exchange rate using NEWFM

Fuzzy neural networks have been successfully applied to generate predictive rules for exchange rate forecasting. This paper presents a methodology to forecast the daily and weekly changes of exchange rate by extracting fuzzy rules based on the neural network with weighted fuzzy membership functions (NEWFM) and the minimized number of input features using the distributed non-overlap area measurement method. NEWFM classifies the higher and lower cases of next daypsilas and next weekpsilas exchange rate using the recent 32 days and 32 weeks of CPP_n,m (Current Price Position of day n and week n : a percentage of the difference between the price of day n and week n and the moving average of the past m days and m weeks from day n-1 and week n-1) of the daily and weekly exchange rate, respectively. In this paper, the Haar wavelet function is used as a mother wavelet. The most important and minimized input features among CPP_n,m and 38 numbers of wavelet transformed coefficients produced by the recent 32 days and 32 weeks of CPP_n,m are selected by the nonoverlap area distribution measurement method. The proposed method shows that the accuracy rates are 55.19% for the daily changes, 72.58% for the weekly changes of GBP/USD exchange rate, and 70.74% for the weekly changes of Indian rupee/USD exchange rate.