Title :
A dynamic neural network method for time series prediction using the KIII model
Author :
Li, Haizhon ; Kozma, Robert
Author_Institution :
Div. of Comput. Sci., Memphis Univ., TN, USA
Abstract :
In this paper, the KIII dynamic neural network is introduced and it is applied to the prediction of complex temporal sequences. In our approach, KIII gives a step-by-step prediction of the direction of the currency exchange rate change. Previously, various multiplayer perceptron (MLP) networks and recurrent neural networks have been successfully implemented for this application. Results obtained by KIII compare favorably with other methods.
Keywords :
forecasting theory; multilayer perceptrons; recurrent neural nets; time series; KIII model; complex temporal sequences; currency exchange rate change; dynamic neural network method; multiplayer perceptron networks; recurrent neural networks; step-by-step prediction; time series prediction; Biological neural networks; Biological system modeling; Biology computing; Brain modeling; Exchange rates; Mathematical model; Nervous system; Neural networks; Neurons; Predictive models;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1223370
