Title :
The Long-Term Predictive Effect of SVM Financial Crisis Early-Warning Model
Author :
Hu, Yanjie ; Su, Peng ; Tang, Fei ; Hao, Xuchun
Author_Institution :
Sch. of Econ. & Manage., Beihang Univ., Beijing, China
Abstract :
Being different from the previous studies, a comprehensive indicator system is constructed in this paper in order to reflect the influence the accounting information quality and corporate governance have on SVM model. This system includes financial indicators, the indicators of accounting information quality and those of corporate governance. Then taking Chinese listed companies of A-stock market in Shenzhen and Shanghai as the sample, SVM model is used to substantiate the superiority of the system. Furthermore, through inspecting the predictive effect of SVM model in the long run, it comes to conclusion that SVM financial early-warning model not only has short-term predictive validity, but also has the long-term one.
Keywords :
financial data processing; support vector machines; A-stock market; accounting information quality; comprehensive indicator system; corporate governance; financial crisis early-warning model; financial indicators; support vector machine; Companies; Conference management; Crisis management; Economic forecasting; Economic indicators; Financial management; Information science; Predictive models; Quality management; Support vector machines;
Conference_Titel :
Information Science and Engineering (ICISE), 2009 1st International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-4909-5
DOI :
10.1109/ICISE.2009.1230