The implementation of dynamic heteroskedasticity convertible SVM model in financial time series

Author

Song Xiaohua ; Zhang Yulin

Author_Institution

Sch. of Econ. & Manage., North China Electr. Power Univ., Beijing, China

fYear

2014

fDate

29-30 Sept. 2014

Firstpage

281

Lastpage

285

Abstract

In this paper, in order to overcome the deficiency of the traditional SVM, a positive mapping between price volatilities and sample periods of underlying financial time series has been assumed according to the theorems of behavioral finance. By embedding this mapping into the constraint equations of the classic SVM algorithm, an improved SVM model named DHC-SVM (Dynamic Heteroskedasticity Convertible SVM) is proposed for the financial price forecasting. Comparing to the classic SVM model, the experimental results on the real-time HS300 index data illustrates that the DHC-SVM has the advantage both in higher accuracy and better stability.

Keywords

financial management; forecasting theory; pricing; time series; DHC-SVM; behavioral finance theorem; classic SVM algorithm; dynamic heteroskedasticity convertible SVM model; financial price forecasting; financial time series; price volatilities; real-time HS300 index data; Accuracy; Data models; Heuristic algorithms; Numerical models; Predictive models; Support vector machines; Time series analysis; DHC-SVM (Dynamic Heteroskedasticity Convertible SVM); Heteroskedasticity GARCH Model; Support Vector Machines (SVM); Transfer Function; behavioral finance; nonlinear classifier;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Research and Technology in Industry Applications (WARTIA), 2014 IEEE Workshop on

Conference_Location

Ottawa, ON

Type

conf

DOI

10.1109/WARTIA.2014.6976252

Filename

6976252