An intelligent credit forecasting system using supervised nonlinear dimensionality reductions

Shian-Chang Huang, Chih Wei Lee, Min Jen Chang, Tung-Kuang Wu

Research output: Contribution to journalArticle

Abstract

Kernel classifiers (such as support vector machines) have been successfully applied in numerous areas, and have demonstrated excellent performance. However, due to the high dimensionality and nonlinear distribution of financial input data in credit rating forecasting, finding a suitable low dimensional subspace by nonlinear dimensionality reductions is a key step to improve classifier performance. By integrating supervised kernel locality preserving projections (SKLPP) with kernel classifiers, this study develops a novel forecasting system for credit ratings. SKLPP is employed to gain a perfect approximation of data manifold and simultaneously preserve local within-class geometric structures according to prior class-label information. Empirical results indicate that, compared with other dimensionality reduction methods, the performance improvement owing to SKLPP is significant. Moreover, the proposed hybrid classifier outperforms other conventional classifiers.

Original languageEnglish
Pages (from-to)851-856
Number of pages6
JournalWorld Academy of Science, Engineering and Technology
Volume65
Publication statusPublished - 2010 May 1

Fingerprint

Classifiers
Support vector machines
Labels

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

@article{53d8e1e888534320952338e28aafa210,
title = "An intelligent credit forecasting system using supervised nonlinear dimensionality reductions",
abstract = "Kernel classifiers (such as support vector machines) have been successfully applied in numerous areas, and have demonstrated excellent performance. However, due to the high dimensionality and nonlinear distribution of financial input data in credit rating forecasting, finding a suitable low dimensional subspace by nonlinear dimensionality reductions is a key step to improve classifier performance. By integrating supervised kernel locality preserving projections (SKLPP) with kernel classifiers, this study develops a novel forecasting system for credit ratings. SKLPP is employed to gain a perfect approximation of data manifold and simultaneously preserve local within-class geometric structures according to prior class-label information. Empirical results indicate that, compared with other dimensionality reduction methods, the performance improvement owing to SKLPP is significant. Moreover, the proposed hybrid classifier outperforms other conventional classifiers.",
author = "Shian-Chang Huang and Lee, {Chih Wei} and Chang, {Min Jen} and Tung-Kuang Wu",
year = "2010",
month = "5",
day = "1",
language = "English",
volume = "65",
pages = "851--856",
journal = "World Academy of Science, Engineering and Technology",
issn = "2010-376X",
publisher = "World Academy of Science Engineering and Technology",

}

An intelligent credit forecasting system using supervised nonlinear dimensionality reductions. / Huang, Shian-Chang; Lee, Chih Wei; Chang, Min Jen; Wu, Tung-Kuang.

In: World Academy of Science, Engineering and Technology, Vol. 65, 01.05.2010, p. 851-856.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An intelligent credit forecasting system using supervised nonlinear dimensionality reductions

AU - Huang, Shian-Chang

AU - Lee, Chih Wei

AU - Chang, Min Jen

AU - Wu, Tung-Kuang

PY - 2010/5/1

Y1 - 2010/5/1

N2 - Kernel classifiers (such as support vector machines) have been successfully applied in numerous areas, and have demonstrated excellent performance. However, due to the high dimensionality and nonlinear distribution of financial input data in credit rating forecasting, finding a suitable low dimensional subspace by nonlinear dimensionality reductions is a key step to improve classifier performance. By integrating supervised kernel locality preserving projections (SKLPP) with kernel classifiers, this study develops a novel forecasting system for credit ratings. SKLPP is employed to gain a perfect approximation of data manifold and simultaneously preserve local within-class geometric structures according to prior class-label information. Empirical results indicate that, compared with other dimensionality reduction methods, the performance improvement owing to SKLPP is significant. Moreover, the proposed hybrid classifier outperforms other conventional classifiers.

AB - Kernel classifiers (such as support vector machines) have been successfully applied in numerous areas, and have demonstrated excellent performance. However, due to the high dimensionality and nonlinear distribution of financial input data in credit rating forecasting, finding a suitable low dimensional subspace by nonlinear dimensionality reductions is a key step to improve classifier performance. By integrating supervised kernel locality preserving projections (SKLPP) with kernel classifiers, this study develops a novel forecasting system for credit ratings. SKLPP is employed to gain a perfect approximation of data manifold and simultaneously preserve local within-class geometric structures according to prior class-label information. Empirical results indicate that, compared with other dimensionality reduction methods, the performance improvement owing to SKLPP is significant. Moreover, the proposed hybrid classifier outperforms other conventional classifiers.

UR - http://www.scopus.com/inward/record.url?scp=78751623775&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78751623775&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:78751623775

VL - 65

SP - 851

EP - 856

JO - World Academy of Science, Engineering and Technology

JF - World Academy of Science, Engineering and Technology

SN - 2010-376X

ER -