Stock Index Prediction and Analysis Based on GASA-SVM

Li Zhe Ma

doi:10.4028/www.scientific.net/AMR.798-799.842

Paper Titles

Analysis on the Micro-Blog Effect in Tourism Management and Marketing under the Net Underground
p.825

The Importance of Exhibition Design in Modern Society
p.829

An Empirical Study of Equity Agency Costs and R&D Intensity: Evidence from Listed Companies on the ChiNext
p.833

Anonymity Query Method of Outsourced Database
p.837

Stock Index Prediction and Analysis Based on GASA-SVM
p.842

Catastrophic Risk, the Disequilibrium of Agricultural Insurance Markets and Reinsurance - Based on the Data from Hubei
p.846

Research on Product Harm Crisis Attributes Influence on Horizontal Spillover Effect – The Moderating Effects of Product Similarity and Corporate Reputation
p.851

The Concept, Formation and Impact of Corporate Reputation in Modern Management Science
p.856

Brief Discussion on Obstacles and Strategies of Furniture Enterprises in Resorting to Third Part Logistics
p.861

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 798-799Stock Index Prediction and Analysis Based on...

Stock Index Prediction and Analysis Based on GASA-SVM

Abstract:

In order to improve the prediction accuracy of stock index, eliminate of the blindness of parameters selection for support vector machine, a stock index prediction method combined the genetic simulated annealing algorithm (GASA) which integrated the parallel search of genetic algorithm with the probabilistic sudden jumping characteristics of simulated annealing algorithm, with support vector machine (SVM) is proposed. Using daily data of Shanghai stock index opening quotation which is normalization processed, the stock index prediction model based on GASA-SVM is established. Optimal parameter error penalty parameter c=1 and Gaussian kernel parameter g=1.625 are obtained. Compared the result with GA-SVM prediction model, the comparative analysis shows that GASA-SVM(MSE= 0.000191111) model prediction capabilities are superior to GA-SVM(MSE=0.000018825) prediction model. It can provide valuable references for the investors.

You might also be interested in these eBooks

Advances in Applied Science and Industrial Technology

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 798-799)

Pages:

842-845

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.798-799.842

Citation:

Cite this paper

Online since:

September 2013

Authors:

Li Zhe Ma

Keywords:

GASA, Prediction, Stock Index, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] M. JIN,C. CHI,J.L. ZHANG,H. ZHANG, Network Security Situation Prediction Model Based on HHCA-RBF Neural Network,. Computer Science, Vol38, pp.70-73, (2011).

Google Scholar

[2] N.Y. DENG.Y.J. TIAN, Support Vector Machines: theory, algorithm and development,. Beijing, CN: Science Press, pp.189-190, (2009).

Google Scholar

[3] VLADIMIR N, Statistical Learning Theory, Beijing, CN: Electronic Industry Press, pp.87-88, (2004).

Google Scholar

[4] L. ZHOU,S.Z. HUANG, Study of Hybrid Genetic Algorithm Based on Simulated Annealing, Application Research of Computers, Vol 9, pp.72-73, (2005).

Google Scholar

[5] H.Y. CHEN, Forecast and Analysis of Shanghai Composite Index Based on Support Vector Machines, computer simulation, Vol 30, pp.297-300, (2013).

Google Scholar