Credit quality assessments using manifold based semi-supervised discriminant analysis and support vector machines

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Due to the large scale of financial data in credit quality forecasting, dimensionality reduction is a key step to enhance classifier performance. By using manifold based semi-supervised discriminant analysis (SSDA) and support vector machines, this study develops a novel prediction system for credit quality assessment, where SSDA makes efficient use of labeled and unlabeled (testing) data points to gain a perfect low dimensional approximation of data manifold and simultaneously maintain the discriminating power. More specifically, the labeled data points are used to maximize the separability between different classes, and the testing data points are used to estimate the intrinsic geometric structure of the data space. Empirical results indicate that SSDA outperforms other dimensionality reduction methods with a significant performance improvement, and our hybrid classifier substantially outperforms other conventional classifiers.

Original languageEnglish
Title of host publicationProceedings - 2011 7th International Conference on Natural Computation, ICNC 2011
Pages2037-2041
Number of pages5
Volume4
DOIs
Publication statusPublished - 2011 Oct 6
Event2011 7th International Conference on Natural Computation, ICNC 2011 - Shanghai, China
Duration: 2011 Jul 262011 Jul 28

Other

Other2011 7th International Conference on Natural Computation, ICNC 2011
CountryChina
CityShanghai
Period11-07-2611-07-28

Fingerprint

Discriminant Analysis
Discriminant analysis
Support vector machines
Classifiers
Testing
Support Vector Machine

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Neuroscience(all)

Cite this

Huang, S-C., & Wu, T-K. (2011). Credit quality assessments using manifold based semi-supervised discriminant analysis and support vector machines. In Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011 (Vol. 4, pp. 2037-2041). [6022386] https://doi.org/10.1109/ICNC.2011.6022386
Huang, Shian-Chang ; Wu, Tung-Kuang. / Credit quality assessments using manifold based semi-supervised discriminant analysis and support vector machines. Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011. Vol. 4 2011. pp. 2037-2041
@inproceedings{baf29636d6384ad68504fe3a5481555e,
title = "Credit quality assessments using manifold based semi-supervised discriminant analysis and support vector machines",
abstract = "Due to the large scale of financial data in credit quality forecasting, dimensionality reduction is a key step to enhance classifier performance. By using manifold based semi-supervised discriminant analysis (SSDA) and support vector machines, this study develops a novel prediction system for credit quality assessment, where SSDA makes efficient use of labeled and unlabeled (testing) data points to gain a perfect low dimensional approximation of data manifold and simultaneously maintain the discriminating power. More specifically, the labeled data points are used to maximize the separability between different classes, and the testing data points are used to estimate the intrinsic geometric structure of the data space. Empirical results indicate that SSDA outperforms other dimensionality reduction methods with a significant performance improvement, and our hybrid classifier substantially outperforms other conventional classifiers.",
author = "Shian-Chang Huang and Tung-Kuang Wu",
year = "2011",
month = "10",
day = "6",
doi = "10.1109/ICNC.2011.6022386",
language = "English",
isbn = "9781424499533",
volume = "4",
pages = "2037--2041",
booktitle = "Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011",

}

Huang, S-C & Wu, T-K 2011, Credit quality assessments using manifold based semi-supervised discriminant analysis and support vector machines. in Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011. vol. 4, 6022386, pp. 2037-2041, 2011 7th International Conference on Natural Computation, ICNC 2011, Shanghai, China, 11-07-26. https://doi.org/10.1109/ICNC.2011.6022386

Credit quality assessments using manifold based semi-supervised discriminant analysis and support vector machines. / Huang, Shian-Chang; Wu, Tung-Kuang.

Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011. Vol. 4 2011. p. 2037-2041 6022386.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Credit quality assessments using manifold based semi-supervised discriminant analysis and support vector machines

AU - Huang, Shian-Chang

AU - Wu, Tung-Kuang

PY - 2011/10/6

Y1 - 2011/10/6

N2 - Due to the large scale of financial data in credit quality forecasting, dimensionality reduction is a key step to enhance classifier performance. By using manifold based semi-supervised discriminant analysis (SSDA) and support vector machines, this study develops a novel prediction system for credit quality assessment, where SSDA makes efficient use of labeled and unlabeled (testing) data points to gain a perfect low dimensional approximation of data manifold and simultaneously maintain the discriminating power. More specifically, the labeled data points are used to maximize the separability between different classes, and the testing data points are used to estimate the intrinsic geometric structure of the data space. Empirical results indicate that SSDA outperforms other dimensionality reduction methods with a significant performance improvement, and our hybrid classifier substantially outperforms other conventional classifiers.

AB - Due to the large scale of financial data in credit quality forecasting, dimensionality reduction is a key step to enhance classifier performance. By using manifold based semi-supervised discriminant analysis (SSDA) and support vector machines, this study develops a novel prediction system for credit quality assessment, where SSDA makes efficient use of labeled and unlabeled (testing) data points to gain a perfect low dimensional approximation of data manifold and simultaneously maintain the discriminating power. More specifically, the labeled data points are used to maximize the separability between different classes, and the testing data points are used to estimate the intrinsic geometric structure of the data space. Empirical results indicate that SSDA outperforms other dimensionality reduction methods with a significant performance improvement, and our hybrid classifier substantially outperforms other conventional classifiers.

UR - http://www.scopus.com/inward/record.url?scp=80053400721&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053400721&partnerID=8YFLogxK

U2 - 10.1109/ICNC.2011.6022386

DO - 10.1109/ICNC.2011.6022386

M3 - Conference contribution

SN - 9781424499533

VL - 4

SP - 2037

EP - 2041

BT - Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011

ER -

Huang S-C, Wu T-K. Credit quality assessments using manifold based semi-supervised discriminant analysis and support vector machines. In Proceedings - 2011 7th International Conference on Natural Computation, ICNC 2011. Vol. 4. 2011. p. 2037-2041. 6022386 https://doi.org/10.1109/ICNC.2011.6022386