Financial time series prediction using polynomial pipelined neural networks

Authors:
Abir Jaafar Hussain;Adam Knowles;Paulo J. G. Lisboa;Wael El-Deredy
Affiliations:
School of Computing and Mathematical Sciences, Liverpool John Moores University, Byrom Street, Liverpool L3 3AF, United Kingdom;School of Computing and Mathematical Sciences, Liverpool John Moores University, Byrom Street, Liverpool L3 3AF, United Kingdom;School of Computing and Mathematical Sciences, Liverpool John Moores University, Byrom Street, Liverpool L3 3AF, United Kingdom;University of Manchester, Oxford Road Manchester, M13 9PL, United Kingdom
Venue:
Expert Systems with Applications: An International Journal
Year:
2008

Citing 8
Cited 4

Multilayer feedforward networks are universal approximators

Neural Networks
On the approximate realization of continuous mappings by neural networks

Neural Networks
Approximation capabilities of multilayer feedforward networks

Neural Networks
A learning algorithm for continually running fully recurrent neural networks

Neural Computation
Nonlinear adaptive prediction of nonstationary signals

IEEE Transactions on Signal Processing
Evolution of functional link networks

IEEE Transactions on Evolutionary Computation
Support vector machine with adaptive parameters in financial time series forecasting

IEEE Transactions on Neural Networks
Stochastic choice of basis functions in adaptive function approximation and the functional-link net

IEEE Transactions on Neural Networks

Model-free adaptive control design using evolutionary-neural compensator

Expert Systems with Applications: An International Journal
Grey system theory-based models in time series prediction

Expert Systems with Applications: An International Journal
Data mining using an adaptive HONN model with hyperbolic tangent neurons

PKAW'10 Proceedings of the 11th international conference on Knowledge management and acquisition for smart systems and services
Save the best for last? The treatment of dominant predictors in financial forecasting

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	12.06

Visualization

Abstract

This paper proposes a novel type of higher-order pipelined neural network: the polynomial pipelined neural network. The proposed network is constructed from a number of higher-order neural networks concatenated with each other to predict highly nonlinear and nonstationary signals based on the engineering concept of divide and conquer. The polynomial pipelined neural network is used to predict the exchange rate between the US dollar and three other currencies. In this application, two sets of experiments are carried out. In the first set, the input data are pre-processed between 0 and 1 and passed to the neural networks as nonstationary data. In the second set of experiments, the nonstationary input signals are transformed into one step relative increase in price. The network demonstrates more accurate forecasting and an improvement in the signal to noise ratio over a number of benchmarked neural networks.