Bankruptcy prediction using multiple intelligent agent system via a localized generalization error approach

Daniel S. YEUNG, W. Y., Wing NG, P. F., Aki CHAN, P. K., Patrick CHAN, Michael FIRTH, C. C., Eric TSANG

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

2 Citations (Scopus)

Abstract

Company Bankruptcy costs a loss of billions of dollars to banks each year. Thus bankruptcy prediction is a critical part of a bank's loan approval decision process. Traditional financial models for bankruptcy prediction are no longer adequate for describing today's complex relationship between the financial health and potential bankruptcy of a company. In this work, a multiple classifier system (embedded in a multiple intelligent agent system) is proposed to predict the financial health of a company. In our model, each individual agent (classifier) makes a prediction on the likelihood of bankruptcy based on only partial information of the company. Each of the agents is an expert, having certain part of the knowledge (represented by features) of the company. The decisions of all agents are combined together to form a final bankruptcy prediction. Preliminary experiments show that our model out-performs other existing methods using the benchmarking Compustat American Corporations dataset.
Original languageEnglish
Title of host publicationProceedings of the 2007 International Conference on Service Systems and Service Management, ICSSSM'07
PublisherInstitute of Electrical and Electronics Engineers
DOIs
Publication statusPublished - 1 Jan 2007

Fingerprint

Intelligent agents
Industry
Classifiers
Health
Benchmarking
Embedded systems
Costs
Experiments

Bibliographical note

Paper presented at the 2007 International Conference on Service Systems and Service Management (ICSSSM'07), 9-11 June 2007, Changdu, China.
ISBN of the source publication: 9781424408856

Cite this

YEUNG, D. S., NG, W. Y. . W., CHAN, P. F. . A., CHAN, P. K. . P., FIRTH, M., & TSANG, C. C. . E. (2007). Bankruptcy prediction using multiple intelligent agent system via a localized generalization error approach. In Proceedings of the 2007 International Conference on Service Systems and Service Management, ICSSSM'07 Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICSSSM.2007.4280079
YEUNG, Daniel S. ; NG, W. Y., Wing ; CHAN, P. F., Aki ; CHAN, P. K., Patrick ; FIRTH, Michael ; TSANG, C. C., Eric. / Bankruptcy prediction using multiple intelligent agent system via a localized generalization error approach. Proceedings of the 2007 International Conference on Service Systems and Service Management, ICSSSM'07. Institute of Electrical and Electronics Engineers, 2007.
@inproceedings{e6c2e6f2850d488d93b5dc1266e5039e,
title = "Bankruptcy prediction using multiple intelligent agent system via a localized generalization error approach",
abstract = "Company Bankruptcy costs a loss of billions of dollars to banks each year. Thus bankruptcy prediction is a critical part of a bank's loan approval decision process. Traditional financial models for bankruptcy prediction are no longer adequate for describing today's complex relationship between the financial health and potential bankruptcy of a company. In this work, a multiple classifier system (embedded in a multiple intelligent agent system) is proposed to predict the financial health of a company. In our model, each individual agent (classifier) makes a prediction on the likelihood of bankruptcy based on only partial information of the company. Each of the agents is an expert, having certain part of the knowledge (represented by features) of the company. The decisions of all agents are combined together to form a final bankruptcy prediction. Preliminary experiments show that our model out-performs other existing methods using the benchmarking Compustat American Corporations dataset.",
author = "YEUNG, {Daniel S.} and NG, {W. Y., Wing} and CHAN, {P. F., Aki} and CHAN, {P. K., Patrick} and Michael FIRTH and TSANG, {C. C., Eric}",
note = "Paper presented at the 2007 International Conference on Service Systems and Service Management (ICSSSM'07), 9-11 June 2007, Changdu, China. ISBN of the source publication: 9781424408856",
year = "2007",
month = "1",
day = "1",
doi = "10.1109/ICSSSM.2007.4280079",
language = "English",
booktitle = "Proceedings of the 2007 International Conference on Service Systems and Service Management, ICSSSM'07",
publisher = "Institute of Electrical and Electronics Engineers",

}

YEUNG, DS, NG, WYW, CHAN, PFA, CHAN, PKP, FIRTH, M & TSANG, CCE 2007, Bankruptcy prediction using multiple intelligent agent system via a localized generalization error approach. in Proceedings of the 2007 International Conference on Service Systems and Service Management, ICSSSM'07. Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICSSSM.2007.4280079

Bankruptcy prediction using multiple intelligent agent system via a localized generalization error approach. / YEUNG, Daniel S.; NG, W. Y., Wing; CHAN, P. F., Aki; CHAN, P. K., Patrick; FIRTH, Michael; TSANG, C. C., Eric.

Proceedings of the 2007 International Conference on Service Systems and Service Management, ICSSSM'07. Institute of Electrical and Electronics Engineers, 2007.

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

TY - GEN

T1 - Bankruptcy prediction using multiple intelligent agent system via a localized generalization error approach

AU - YEUNG, Daniel S.

AU - NG, W. Y., Wing

AU - CHAN, P. F., Aki

AU - CHAN, P. K., Patrick

AU - FIRTH, Michael

AU - TSANG, C. C., Eric

N1 - Paper presented at the 2007 International Conference on Service Systems and Service Management (ICSSSM'07), 9-11 June 2007, Changdu, China. ISBN of the source publication: 9781424408856

PY - 2007/1/1

Y1 - 2007/1/1

N2 - Company Bankruptcy costs a loss of billions of dollars to banks each year. Thus bankruptcy prediction is a critical part of a bank's loan approval decision process. Traditional financial models for bankruptcy prediction are no longer adequate for describing today's complex relationship between the financial health and potential bankruptcy of a company. In this work, a multiple classifier system (embedded in a multiple intelligent agent system) is proposed to predict the financial health of a company. In our model, each individual agent (classifier) makes a prediction on the likelihood of bankruptcy based on only partial information of the company. Each of the agents is an expert, having certain part of the knowledge (represented by features) of the company. The decisions of all agents are combined together to form a final bankruptcy prediction. Preliminary experiments show that our model out-performs other existing methods using the benchmarking Compustat American Corporations dataset.

AB - Company Bankruptcy costs a loss of billions of dollars to banks each year. Thus bankruptcy prediction is a critical part of a bank's loan approval decision process. Traditional financial models for bankruptcy prediction are no longer adequate for describing today's complex relationship between the financial health and potential bankruptcy of a company. In this work, a multiple classifier system (embedded in a multiple intelligent agent system) is proposed to predict the financial health of a company. In our model, each individual agent (classifier) makes a prediction on the likelihood of bankruptcy based on only partial information of the company. Each of the agents is an expert, having certain part of the knowledge (represented by features) of the company. The decisions of all agents are combined together to form a final bankruptcy prediction. Preliminary experiments show that our model out-performs other existing methods using the benchmarking Compustat American Corporations dataset.

UR - http://commons.ln.edu.hk/sw_master/7042

U2 - 10.1109/ICSSSM.2007.4280079

DO - 10.1109/ICSSSM.2007.4280079

M3 - Conference paper (refereed)

BT - Proceedings of the 2007 International Conference on Service Systems and Service Management, ICSSSM'07

PB - Institute of Electrical and Electronics Engineers

ER -

YEUNG DS, NG WYW, CHAN PFA, CHAN PKP, FIRTH M, TSANG CCE. Bankruptcy prediction using multiple intelligent agent system via a localized generalization error approach. In Proceedings of the 2007 International Conference on Service Systems and Service Management, ICSSSM'07. Institute of Electrical and Electronics Engineers. 2007 https://doi.org/10.1109/ICSSSM.2007.4280079