| Author: | Wong, Chor-heung Verena |
| Title: | Credit risk management in financial institutions |
| Degree: | M.B.A. |
| Year: | 1999 |
| Subject: | Bank management Risk management Neural networks (Computer science) -- Design and construction Hong Kong Polytechnic University -- Dissertations |
| Department: | Department of Management |
| Pages: | v, 91, [71] leaves : ill. ; 30 cm |
| Language: | English |
| Abstract: | Credit risk management becoming significantly important to financial institutions during the current Asian financial crisis. Being able to form highly reliable early forecasts of the future health of companies is critically important to bank lending officers. One of the widely adopted model in the United States to evaluate the financial health of a company is the Z-score developed by Edward I. Altman thirty years before. It was found that the model is not so reliable by computing our selected samples as overall forecast error was over 50%. If Z-score had to used to predict Hong Kong companies, coefficient used had to adjust. This study compares the predictive capabilities for loan classification of neural networks and classical multivariate discriminant analysis Z-score. This study found that neural network performs significantly better than the Z-score at loan classification. Forecasting error on all case is below 10%. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b14718637.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 4.86 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/2350