An Innovative Use of Historical Data for Neural Network Based Stock Prediction

DOI

10.2991/jcis.2006.153How to use a DOI?

Keywords

prediction, stock time series, artificial neural network, time point selection

Abstract

Using artificial neural network is a common approach for the stock time series prediction problem. Unlike variety of researches that focus on selecting different indicators, network training, network architecture, etc., we are focusing on the selection of appropriate time points from the time sequence to serve as the input of the neural network prediction system for dimensionality reduction. We propose to select the time points based on data point importance using perceptually important point identification process. The empirical result shows that the proposed method generally outperformed the traditional method using uniform time delay.

Copyright

© 2006, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Tak-chung Fu
AU  - Tsz-leung Cheung
AU  - Fu-lai Chung
AU  - Chak-man Ng
PY  - 2006/10
DA  - 2006/10
TI  - An Innovative Use of Historical Data for Neural Network Based Stock Prediction
BT  - Proceedings of the 9th Joint International Conference on Information Sciences (JCIS-06)
PB  - Atlantis Press
SP  - 685
EP  - 688
SN  - 1951-6851
UR  - https://doi.org/10.2991/jcis.2006.153
DO  - 10.2991/jcis.2006.153
ID  - Fu2006/10
ER  -