Application of Ridge Polynomial Neural Networks to Financial Time Series Prediction

This paper presents a novel application of ridge polynomial neural network to forecast the future trends of financial time series data. The prediction capability of ridge polynomial neural network was tested on four different data sets; the US/EU exchange rate, the UK/EU exchange rate, the JP/EU exchange rate, and the IBM common stock closing price. The performance of the network is benchmarked against the performance of multilayer perceptron, functional link neural network, and pi-sigma neural network. The predictions demonstrated that ridge polynomial neural network brings in more return in comparison to other models. It is observed that the network is able to find an appropriate input output mapping of various chaotic financial time series data with a good performance in learning speed and generalization capability.