An ICA design of intraday stock prediction models with automatic variable selection
Refereed conference paper presented and published in conference proceedings

CUHK Authors
Author(s) no longer affiliated with CUHK


Full Text

Times Cited
Web of Science10WOS source URL (as at 08/08/2020) Click here for the latest count

Other information
AbstractIndependent component analysis (ICA) provides a mechanism of decomposing non-Gaussian data signals into statistically independent components. In this paper, ICA is used to extract the underlying news factors from intraday stock data. A prediction algorithm is developed to improve stock index predictions using such extracted "news". Both linear regression model and nonlinear artificial neural network model are proposed to predict stock indexes of Open, Close, High and Low using the ICA extracted "news". These models are compared with models using only raw intraday data as "news". It is demonstrated that ICA helps in extracting market underlying affecting "news", and thus improves the stock prediction accuracy. It shows that the proposed ICA prediction algorithm is a simple to use and versatile algorithm that automatically extracts the most relevant news for different stock index predictions.
All Author(s) ListMok PY, Lam KP, Ng HS
Name of ConferenceIEEE International Joint Conference on Neural Networks (IJCNN)
Start Date of Conference25/07/2004
End Date of Conference29/07/2004
Place of ConferenceBudapest
Country/Region of ConferenceHungary
Year2004
Month1
Day1
PublisherIEEE
Pages2135 - 2140
ISBN0-7803-8359-1
ISSN1098-7576
LanguagesEnglish-United Kingdom
Keywordsindependent component analysis; linear regression; neural network
Web of Science Subject CategoriesComputer Science; Computer Science, Artificial Intelligence; Computer Science, Cybernetics

Last updated on 2020-09-08 at 04:23