Financial Distress Prediction of Chinese-Listed Companies Based on PCA and WNNs

Xiu Xin and Xiaoyi Xiong
Additional contact information
Xiu Xin: Hebei Finance University, China
Xiaoyi Xiong: Hebei Finance University, China

International Journal of Advanced Pervasive and Ubiquitous Computing (IJAPUC), 2011, vol. 3, issue 4, 6-14

Abstract: The operating status of an enterprise is disclosed periodically in a financial statement. Financial distress prediction is important for business bankruptcy prevention, and various quantitative prediction methods based on financial ratios have been proposed. This paper presents a financial distress prediction model based on wavelet neural networks (WNNs). The transfer functions of the neurons in WNNs are wavelet base functions which are determined by dilation and translation factors. Back propagation algorithm was used to train the WNNs. Principal component analysis (PCA) method was used to reduce the dimension of the inputs of the WNNs. Multiple discriminate analysis (MDA), Logit, Probit, and WNNs were employed to a dataset selected from Chinese-listed companies. The results demonstrate that the proposed WNNs-based model performs well in comparison with the other three models.

Date: 2011
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 018/japuc.2011100102 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:japuc0:v:3:y:2011:i:4:p:6-14

Access Statistics for this article

International Journal of Advanced Pervasive and Ubiquitous Computing (IJAPUC) is currently edited by Tao Gao

More articles in International Journal of Advanced Pervasive and Ubiquitous Computing (IJAPUC) from IGI Global
Bibliographic data for series maintained by Journal Editor ().