Research and application of PSO-BP neural networks in credit risk assessment

Ning Liu; En Jun Xia; Li Yang

doi:10.1109/ISCID.2010.41

Research and application of PSO-BP neural networks in credit risk assessment

Ning Liu^*, En Jun Xia, Li Yang

^*Corresponding author for this work

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

3 Citations (Scopus)

Abstract

According to the complexity of financial system, the model of credit risk assessment based on PSO algorithm and BP neural network integrated is proposed, which in order to improve the accuracy and reliability of risk assessment. First the neural network model of a credit risk evaluation is created, and then PSO algorithm is introduced to optimize the weight and threshold of the neural network, at last, using the indexes and regarding relevant data of 250 enterprises as sample, the BP neural network is trained and tested. Compared with the traditional calculation methods, experimental results show that the method is a feasible and effective assessment method with fast convergence and high precision prediction.

Original language	English
Title of host publication	Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010
Publisher	IEEE Computer Society
Pages	103-106
Number of pages	4
ISBN (Print)	9780769541983
DOIs	https://doi.org/10.1109/ISCID.2010.41
Publication status	Published - 2010
Event	2010 International Symposium on Computational Intelligence and Design, ISCID 2010 - Hangzhou, China Duration: 29 Oct 2010 → 31 Oct 2010

Publication series

Name	Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010
Volume	1

Conference

Conference	2010 International Symposium on Computational Intelligence and Design, ISCID 2010
Country/Territory	China
City	Hangzhou
Period	29/10/10 → 31/10/10

Keywords

BP neural network
Credit risk
Particle swarm optimization
Risk assessment

Access to Document

10.1109/ISCID.2010.41

Cite this

Liu, N., Xia, E. J., & Yang, L. (2010). Research and application of PSO-BP neural networks in credit risk assessment. In Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010 (pp. 103-106). Article 5692674 (Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010; Vol. 1). IEEE Computer Society. https://doi.org/10.1109/ISCID.2010.41

@inproceedings{186e13e9d2054f13a8f7f16c7c1412a1,

title = "Research and application of PSO-BP neural networks in credit risk assessment",

abstract = "According to the complexity of financial system, the model of credit risk assessment based on PSO algorithm and BP neural network integrated is proposed, which in order to improve the accuracy and reliability of risk assessment. First the neural network model of a credit risk evaluation is created, and then PSO algorithm is introduced to optimize the weight and threshold of the neural network, at last, using the indexes and regarding relevant data of 250 enterprises as sample, the BP neural network is trained and tested. Compared with the traditional calculation methods, experimental results show that the method is a feasible and effective assessment method with fast convergence and high precision prediction.",

keywords = "BP neural network, Credit risk, Particle swarm optimization, Risk assessment",

author = "Ning Liu and Xia, {En Jun} and Li Yang",

year = "2010",

doi = "10.1109/ISCID.2010.41",

language = "English",

isbn = "9780769541983",

series = "Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010",

publisher = "IEEE Computer Society",

pages = "103--106",

booktitle = "Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010",

address = "United States",

note = "2010 International Symposium on Computational Intelligence and Design, ISCID 2010 ; Conference date: 29-10-2010 Through 31-10-2010",

}

Liu, N, Xia, EJ & Yang, L 2010, Research and application of PSO-BP neural networks in credit risk assessment. in Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010., 5692674, Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010, vol. 1, IEEE Computer Society, pp. 103-106, 2010 International Symposium on Computational Intelligence and Design, ISCID 2010, Hangzhou, China, 29/10/10. https://doi.org/10.1109/ISCID.2010.41

Research and application of PSO-BP neural networks in credit risk assessment. / Liu, Ning; Xia, En Jun; Yang, Li.
Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010. IEEE Computer Society, 2010. p. 103-106 5692674 (Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010; Vol. 1).

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

TY - GEN

T1 - Research and application of PSO-BP neural networks in credit risk assessment

AU - Liu, Ning

AU - Xia, En Jun

AU - Yang, Li

PY - 2010

Y1 - 2010

N2 - According to the complexity of financial system, the model of credit risk assessment based on PSO algorithm and BP neural network integrated is proposed, which in order to improve the accuracy and reliability of risk assessment. First the neural network model of a credit risk evaluation is created, and then PSO algorithm is introduced to optimize the weight and threshold of the neural network, at last, using the indexes and regarding relevant data of 250 enterprises as sample, the BP neural network is trained and tested. Compared with the traditional calculation methods, experimental results show that the method is a feasible and effective assessment method with fast convergence and high precision prediction.

AB - According to the complexity of financial system, the model of credit risk assessment based on PSO algorithm and BP neural network integrated is proposed, which in order to improve the accuracy and reliability of risk assessment. First the neural network model of a credit risk evaluation is created, and then PSO algorithm is introduced to optimize the weight and threshold of the neural network, at last, using the indexes and regarding relevant data of 250 enterprises as sample, the BP neural network is trained and tested. Compared with the traditional calculation methods, experimental results show that the method is a feasible and effective assessment method with fast convergence and high precision prediction.

KW - BP neural network

KW - Credit risk

KW - Particle swarm optimization

KW - Risk assessment

UR - http://www.scopus.com/inward/record.url?scp=79951635770&partnerID=8YFLogxK

U2 - 10.1109/ISCID.2010.41

DO - 10.1109/ISCID.2010.41

M3 - Conference contribution

AN - SCOPUS:79951635770

SN - 9780769541983

T3 - Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010

SP - 103

EP - 106

BT - Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010

PB - IEEE Computer Society

T2 - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010

Y2 - 29 October 2010 through 31 October 2010

ER -

Liu N, Xia EJ, Yang L. Research and application of PSO-BP neural networks in credit risk assessment. In Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010. IEEE Computer Society. 2010. p. 103-106. 5692674. (Proceedings - 2010 International Symposium on Computational Intelligence and Design, ISCID 2010). doi: 10.1109/ISCID.2010.41

Research and application of PSO-BP neural networks in credit risk assessment

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this