Integrating GA-based time-scale feature extractions with SVMs for stock index forecasting

Research output: Contribution to journalArticle

43 Citations (Scopus)

Abstract

By integrating genetic algorithm (GA)-based optimal time-scale feature extractions with support vector machines (SVM), this study develops a novel hybrid prediction model that operates for multiple time-scale resolutions and utilizes a flexible nonparametric regressor to predict future evolutions of various stock indices. The time series of explanatory variables are decomposed using wavelet bases, and a GA is employed to extract optimal time-scale feature subsets from decomposed features. These extracted time-scale feature subsets then serve as an input for an SVM model that performs final forecasting. Compared with neural networks, pure SVMs or traditional GARCH models, the proposed model performs best. The root-mean-squared forecasting errors are significantly reduced.

Original languageEnglish
Pages (from-to)2080-2088
Number of pages9
JournalExpert Systems with Applications
Volume35
Issue number4
DOIs
Publication statusPublished - 2008 Nov 1

Fingerprint

Feature extraction
Genetic algorithms
Support vector machines
Time series
Neural networks

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

@article{602dcc765ba44653a32b58d336bc4817,
title = "Integrating GA-based time-scale feature extractions with SVMs for stock index forecasting",
abstract = "By integrating genetic algorithm (GA)-based optimal time-scale feature extractions with support vector machines (SVM), this study develops a novel hybrid prediction model that operates for multiple time-scale resolutions and utilizes a flexible nonparametric regressor to predict future evolutions of various stock indices. The time series of explanatory variables are decomposed using wavelet bases, and a GA is employed to extract optimal time-scale feature subsets from decomposed features. These extracted time-scale feature subsets then serve as an input for an SVM model that performs final forecasting. Compared with neural networks, pure SVMs or traditional GARCH models, the proposed model performs best. The root-mean-squared forecasting errors are significantly reduced.",
author = "Huang, {Shian Chang} and Wu, {Tung Kuang}",
year = "2008",
month = "11",
day = "1",
doi = "10.1016/j.eswa.2007.09.027",
language = "English",
volume = "35",
pages = "2080--2088",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "4",

}

Integrating GA-based time-scale feature extractions with SVMs for stock index forecasting. / Huang, Shian Chang; Wu, Tung Kuang.

In: Expert Systems with Applications, Vol. 35, No. 4, 01.11.2008, p. 2080-2088.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Integrating GA-based time-scale feature extractions with SVMs for stock index forecasting

AU - Huang, Shian Chang

AU - Wu, Tung Kuang

PY - 2008/11/1

Y1 - 2008/11/1

N2 - By integrating genetic algorithm (GA)-based optimal time-scale feature extractions with support vector machines (SVM), this study develops a novel hybrid prediction model that operates for multiple time-scale resolutions and utilizes a flexible nonparametric regressor to predict future evolutions of various stock indices. The time series of explanatory variables are decomposed using wavelet bases, and a GA is employed to extract optimal time-scale feature subsets from decomposed features. These extracted time-scale feature subsets then serve as an input for an SVM model that performs final forecasting. Compared with neural networks, pure SVMs or traditional GARCH models, the proposed model performs best. The root-mean-squared forecasting errors are significantly reduced.

AB - By integrating genetic algorithm (GA)-based optimal time-scale feature extractions with support vector machines (SVM), this study develops a novel hybrid prediction model that operates for multiple time-scale resolutions and utilizes a flexible nonparametric regressor to predict future evolutions of various stock indices. The time series of explanatory variables are decomposed using wavelet bases, and a GA is employed to extract optimal time-scale feature subsets from decomposed features. These extracted time-scale feature subsets then serve as an input for an SVM model that performs final forecasting. Compared with neural networks, pure SVMs or traditional GARCH models, the proposed model performs best. The root-mean-squared forecasting errors are significantly reduced.

UR - http://www.scopus.com/inward/record.url?scp=48749133695&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48749133695&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2007.09.027

DO - 10.1016/j.eswa.2007.09.027

M3 - Article

AN - SCOPUS:48749133695

VL - 35

SP - 2080

EP - 2088

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 4

ER -