Combined model of empirical study for credit risk management

Lu Han; Liyan Han; Hongwei Zhao

doi:10.1109/ICIFE.2010.5609281

Combined model of empirical study for credit risk management

Lu Han^*
, Liyan Han^*
, Hongwei Zhao

^*Corresponding author for this work

School of Economics and Management

Beihang University
Rainier Technology Co., Ltd.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

In this paper, we studied the two most commonly used artificial intelligence methods (Multilayer Perceptron and Radial Basis Function network) to build the credit scoring model of applications, and analyzed the most important restraining factors of the applications of neural network which is the exponential increase in the variables bringing the model over-complex. On this basis, the author combines econometric analysis of the experience, through logistic regression the model can filter the variables with a high degree of correlation, which greatly reduces the complexity of the model, while the model has a better explanation, and thus improve the effect of neural network prediction models. The method can also be used for a variety of artificial intelligence applications to improve forecast model results.

Original language	English
Title of host publication	Proceedings - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010
Pages	189-192
Number of pages	4
DOIs	https://doi.org/10.1109/ICIFE.2010.5609281
State	Published - 2010
Event	2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010 - Chongqing, China Duration: 17 Sep 2010 → 19 Sep 2010

Publication series

Name	Proceedings - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010

Conference

Conference	2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010
Country/Territory	China
City	Chongqing
Period	17/09/10 → 19/09/10

Keywords

Credit risk
Logistic regression
Multilayer perceptron
Neural networks
Radial basis function

Access to Document

10.1109/ICIFE.2010.5609281

Cite this

Han, L., Han, L., & Zhao, H. (2010). Combined model of empirical study for credit risk management. In Proceedings - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010 (pp. 189-192). Article 5609281 (Proceedings - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010). https://doi.org/10.1109/ICIFE.2010.5609281

@inproceedings{cdada1238e55404dbd62f0d39dfdbdf4,

title = "Combined model of empirical study for credit risk management",

abstract = "In this paper, we studied the two most commonly used artificial intelligence methods (Multilayer Perceptron and Radial Basis Function network) to build the credit scoring model of applications, and analyzed the most important restraining factors of the applications of neural network which is the exponential increase in the variables bringing the model over-complex. On this basis, the author combines econometric analysis of the experience, through logistic regression the model can filter the variables with a high degree of correlation, which greatly reduces the complexity of the model, while the model has a better explanation, and thus improve the effect of neural network prediction models. The method can also be used for a variety of artificial intelligence applications to improve forecast model results.",

keywords = "Credit risk, Logistic regression, Multilayer perceptron, Neural networks, Radial basis function",

author = "Lu Han and Liyan Han and Hongwei Zhao",

year = "2010",

doi = "10.1109/ICIFE.2010.5609281",

language = "英语",

isbn = "9781424469253",

series = "Proceedings - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010",

pages = "189--192",

booktitle = "Proceedings - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010",

note = "2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010 ; Conference date: 17-09-2010 Through 19-09-2010",

}

Han, L, Han, L & Zhao, H 2010, Combined model of empirical study for credit risk management. in Proceedings - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010., 5609281, Proceedings - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010, pp. 189-192, 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010, Chongqing, China, 17/09/10. https://doi.org/10.1109/ICIFE.2010.5609281

Combined model of empirical study for credit risk management. / Han, Lu; Han, Liyan; Zhao, Hongwei.
Proceedings - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010. 2010. p. 189-192 5609281 (Proceedings - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Combined model of empirical study for credit risk management

AU - Han, Lu

AU - Han, Liyan

AU - Zhao, Hongwei

PY - 2010

Y1 - 2010

N2 - In this paper, we studied the two most commonly used artificial intelligence methods (Multilayer Perceptron and Radial Basis Function network) to build the credit scoring model of applications, and analyzed the most important restraining factors of the applications of neural network which is the exponential increase in the variables bringing the model over-complex. On this basis, the author combines econometric analysis of the experience, through logistic regression the model can filter the variables with a high degree of correlation, which greatly reduces the complexity of the model, while the model has a better explanation, and thus improve the effect of neural network prediction models. The method can also be used for a variety of artificial intelligence applications to improve forecast model results.

AB - In this paper, we studied the two most commonly used artificial intelligence methods (Multilayer Perceptron and Radial Basis Function network) to build the credit scoring model of applications, and analyzed the most important restraining factors of the applications of neural network which is the exponential increase in the variables bringing the model over-complex. On this basis, the author combines econometric analysis of the experience, through logistic regression the model can filter the variables with a high degree of correlation, which greatly reduces the complexity of the model, while the model has a better explanation, and thus improve the effect of neural network prediction models. The method can also be used for a variety of artificial intelligence applications to improve forecast model results.

KW - Credit risk

KW - Logistic regression

KW - Multilayer perceptron

KW - Neural networks

KW - Radial basis function

UR - https://www.scopus.com/pages/publications/78650275517

U2 - 10.1109/ICIFE.2010.5609281

DO - 10.1109/ICIFE.2010.5609281

M3 - 会议稿件

AN - SCOPUS:78650275517

SN - 9781424469253

T3 - Proceedings - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010

SP - 189

EP - 192

BT - Proceedings - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010

T2 - 2010 2nd IEEE International Conference on Information and Financial Engineering, ICIFE 2010

Y2 - 17 September 2010 through 19 September 2010

ER -

Combined model of empirical study for credit risk management

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this