Author: | Che, Yin-hong Patrick |
Title: | An expert system prototype for advising the acceptability of insurance applications |
Degree: | M.Sc. |
Year: | 1997 |
Subject: | Insurance -- Planning Expert systems (Computer science) Hong Kong Polytechnic University -- Dissertations |
Department: | Department of Computing |
Pages: | 133 leaves : ill. ; 30 cm |
Language: | English |
Abstract: | To determine the acceptability of insurance applications is part of the underwriting process. And the purpose of underwriting is to choose to cover, from all the risks which are proposed to the insurer, those which collectively will be profitable. To underwriter, judgment has to be made on whether the proposal is acceptable. This judgment is based on the experience of underwriter. As underwriter always operate in conditions of uncertainty, their decision-making is often intuitive: relying on previous experience and information which may be available to conceive a largely informal and unverbalised analysis of options. The purpose of this dissertation is to develop an expert system prototype to perform part of the underwriting tasks currently undertaken by human experts; that is to determine the acceptability of insurance applications by employing fuzzy logic and fuzzy measure in a rule-based system to handle uncertainty. It is expected that the expert system will not only speed up the insurance applications processing time by allowing decision-making process to be distributed at the point-of-sale, but also achieve resource utilization by eventually allowing all bank insurance executives to function as effectively as the expert underwriters. A Fuzzy rule-based system was formulated from knowledge of factors that may influence the selection process, expert considerations of how imprecise modes of reasoning is carried out by using linguistic variables and fuzzy measure in an environment of uncertainty and imprecision. The KAPPAC-PC expert system shell is adopted for the system development. Evaluation and testing are carried out at the end of the development stage. The result of evaluation is acceptable given only a small number of factors are considered by the prototype. To develop a complete expert system, more factors need to be evaluated and more intermediate truth values for these factors are also needed to be considered. In this research project, I only consider one to two truth values for a factor to illustrate the application of fuzzy logic in building the expert system prototype. |
Rights: | All rights reserved |
Access: | restricted access |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
b14054309.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 4.91 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/200/645