Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Computing | en_US |
| dc.creator | Chan, Hok-sum | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/5168 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | An intelligent system for assessing risk management in commercial banks | en_US |
| dcterms.abstract | Throughout all these years, banks have exercised extreme caution in granting credits to clients. However, the control over the excessive utilization of the pre-approved credit facilities is an area where many banks have faced difficulties. Clients always try to maximize the usage of the bank offered facilities in order to take the best advantage of doing their business. Therefore, overdrawing the credit facilities is very common in everyday banking operations. On the one hand, banks normally will not reject the clients right away when overdrawn transactions are presented by them as it would hurt the well established relationship between the clients and the banks. On the other band, there is no strict rule for the bank employees to follow so that overdrawn transactions presented by particular clients can be unconditionally accepted. Conflicting decisions are always made which constitute arguments between risk control staff and business promotion staff. They always plead each other that they are not seeing things in the right angle. For the past years, Artificial Neural Network (ANN) has been widely studied in the academic field and even adopted by some organizations in Western Countries in solving their problems relating to forecasting, classification and pattern recognition. The result has been quite promising and fruitful. But up to this writing, no study has attempted to model the decision making process of the risk managers in arriving the decision of either 'accept' or 'reject' the overdrawn transactions presented. This study tries to serve as a starting point to apply ANN in tackling risk management issues in the field of banking industry regarding the decision making on whether 'accept' or 'reject' the overdrawn transactions presented by clients. ANN is used to mimic what risk managers do during the approval processes. Results generated by ANN will be compared with that generated by a statistical tool - Discriminant Analysis (DA) and see if systems built by ANN is really feasible for further development in the banking industry. | en_US |
| dcterms.extent | 102, [10] leaves : ill. ; 30 cm | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 1998 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Banks and banking | en_US |
| dcterms.LCSH | Neural networks (Computer science) -- Design and construction | en_US |
| dcterms.LCSH | Risk management | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b14391648.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.34 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/200/5168