Skip to content
Back to outputs

A novel dual-weighted fuzzy proximal support vector machine with application to credit risk analysis

Research output: Contribution to journalArticle

Standard

A novel dual-weighted fuzzy proximal support vector machine with application to credit risk analysis. / Yu, Lean; Yao, Xiao; Zhang, Xiaoming; Yin, Hang; Liu, Jia.

In: International Review of Financial Analysis, Vol. 71, 101577, 01.10.2020.

Research output: Contribution to journalArticle

Harvard

Yu, L, Yao, X, Zhang, X, Yin, H & Liu, J 2020, 'A novel dual-weighted fuzzy proximal support vector machine with application to credit risk analysis', International Review of Financial Analysis, vol. 71, 101577. https://doi.org/10.1016/j.irfa.2020.101577

APA

Yu, L., Yao, X., Zhang, X., Yin, H., & Liu, J. (2020). A novel dual-weighted fuzzy proximal support vector machine with application to credit risk analysis. International Review of Financial Analysis, 71, [101577]. https://doi.org/10.1016/j.irfa.2020.101577

Vancouver

Author

Yu, Lean ; Yao, Xiao ; Zhang, Xiaoming ; Yin, Hang ; Liu, Jia. / A novel dual-weighted fuzzy proximal support vector machine with application to credit risk analysis. In: International Review of Financial Analysis. 2020 ; Vol. 71.

Bibtex

@article{7a835062593542e18ae39470e4c63de5,
title = "A novel dual-weighted fuzzy proximal support vector machine with application to credit risk analysis",
abstract = "In this paper, a novel dual-weighted fuzzy proximal support vector machine (FPSVM) model hybridizing fuzzy set theory (FST) and proximal support vector machine (PSVM) is proposed for credit risk analysis. In the proposed model, the fuzzy memberships are introduced into both objective function and constraint conditions of PSVM model to make full use of the information of data. Due to the introduction of fuzzy set theory, the FPSVM model shows fine generalized ability and great practical value. For verification purpose, two publicly available credit datasets are used to test the effectiveness of the proposed FPSVM method. Experimental results show that the proposed FPSVM outperforms other SVM models listed in this study, indicating that the proposed FPSVM model has rather good discriminatory power and it can be used as a promising tool for other classification tasks.",
keywords = "Credit risk analysis, Support vector machine, Fuzzy memberships, Dual-weighted fuzzy PSVM, embargoover12",
author = "Lean Yu and Xiao Yao and Xiaoming Zhang and Hang Yin and Jia Liu",
year = "2020",
month = oct,
day = "1",
doi = "10.1016/j.irfa.2020.101577",
language = "English",
volume = "71",
journal = "International Review of Financial Analysis",
issn = "1057-5219",
publisher = "Elsevier Inc.",

}

RIS

TY - JOUR

T1 - A novel dual-weighted fuzzy proximal support vector machine with application to credit risk analysis

AU - Yu, Lean

AU - Yao, Xiao

AU - Zhang, Xiaoming

AU - Yin, Hang

AU - Liu, Jia

PY - 2020/10/1

Y1 - 2020/10/1

N2 - In this paper, a novel dual-weighted fuzzy proximal support vector machine (FPSVM) model hybridizing fuzzy set theory (FST) and proximal support vector machine (PSVM) is proposed for credit risk analysis. In the proposed model, the fuzzy memberships are introduced into both objective function and constraint conditions of PSVM model to make full use of the information of data. Due to the introduction of fuzzy set theory, the FPSVM model shows fine generalized ability and great practical value. For verification purpose, two publicly available credit datasets are used to test the effectiveness of the proposed FPSVM method. Experimental results show that the proposed FPSVM outperforms other SVM models listed in this study, indicating that the proposed FPSVM model has rather good discriminatory power and it can be used as a promising tool for other classification tasks.

AB - In this paper, a novel dual-weighted fuzzy proximal support vector machine (FPSVM) model hybridizing fuzzy set theory (FST) and proximal support vector machine (PSVM) is proposed for credit risk analysis. In the proposed model, the fuzzy memberships are introduced into both objective function and constraint conditions of PSVM model to make full use of the information of data. Due to the introduction of fuzzy set theory, the FPSVM model shows fine generalized ability and great practical value. For verification purpose, two publicly available credit datasets are used to test the effectiveness of the proposed FPSVM method. Experimental results show that the proposed FPSVM outperforms other SVM models listed in this study, indicating that the proposed FPSVM model has rather good discriminatory power and it can be used as a promising tool for other classification tasks.

KW - Credit risk analysis

KW - Support vector machine

KW - Fuzzy memberships

KW - Dual-weighted fuzzy PSVM

KW - embargoover12

UR - https://linkinghub.elsevier.com/retrieve/pii/S1057521920302210

U2 - 10.1016/j.irfa.2020.101577

DO - 10.1016/j.irfa.2020.101577

M3 - Article

VL - 71

JO - International Review of Financial Analysis

JF - International Review of Financial Analysis

SN - 1057-5219

M1 - 101577

ER -

ID: 22979050