The Integrated Methodology of KPCA and Wavelet Support Vector Machine for Predicting Financial Distress

Authors:
Jian-Guo Zhou;Tao Bai;Ji-Ming Tian
Affiliations:
School of Business Administration, North China Electric Power University, Baoding, China 071003;School of Business Administration, North China Electric Power University, Baoding, China 071003;School of Business Administration, North China Electric Power University, Baoding, China 071003
Venue:
ADMA '08 Proceedings of the 4th international conference on Advanced Data Mining and Applications
Year:
2008

Citing 4
Cited 0

Bankruptcy prediction using neural networks

Decision Support Systems - Special issue on neural networks for decision support
Nonlinear component analysis as a kernel eigenvalue problem

Neural Computation
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Hybrid wavelet-support vector classification of waveforms

Journal of Computational and Applied Mathematics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a hybrid intelligent system, combining kernel principal component analysis (KPCA) and wavelet support vector machine (WSVM), is applied to the study of predicting financial distress. KPCA method is used as a preprocessor of classifier to extract the nonlinear features of input variables. Then a method that generates wavelet kernel function of the SVM is proposed based on the theory of wavelet frame and the condition of the SVM kernel function. The Mexican Hat wavelet is selected to construct the SVM kernel function and form the wavelet support vector machine (WSVM). The effectiveness of the proposed model is verified by experiments through the contrast of the results of SVMs with different kernel functions and other models.