Dynamic Ridge Polynomial Neural Network for Financial Time Series Prediction

Abstract

This paper presents a novel type of higher-order polynomial recurrent neural network called the dynamic ridge polynomial neural network. The aim of the proposed network is to improve the performance of the ridge polynomial neural network by accommodating recurrent links structure. The network is tested for the prediction of non-linear and non-stationary financial signals. Two exchange rates time-series, which are the exchange rate time series between the British pound and the euro as well as the US dollar and the euro, are used in the simulation process. Simulation results showed that dynamic ridge polynomial neural networks generate higher profit returns with fast convergence when used to predict noisy financial time series