Multiple dimensioned mining of financial fluctuation through radial basis function networks

Fluctuation mining is one of the greatest challenging tasks in the field of finance market. The main contribution of this research was to propose a multiple dimensioned model for financial market fluctuation mining. In this approach, the original financial time series is broken down into different information by the wavelet filtering technique, and then, all this information is handled through radial basis function networks due to its universal approximation abilities and more robust than the ordinary networks. An experimental analysis is conducted with the proposed model using stock index future time series, revealing consistent performance improvement of this kind of multidimensional approach.