An expert system for the reallocation of orphan policies in an insurance company

Pao Yue-kong Library Electronic Theses Database

An expert system for the reallocation of orphan policies in an insurance company

 

Author: Lam, Ying-wai, Alan
Title: An expert system for the reallocation of orphan policies in an insurance company
Degree: M.Sc.
Year: 1996
Subject: Insurance, Life -- Policies
Insurance, Life -- Hong Kong
Life insurance agents
Expert systems (Computer science)
Hong Kong Polytechnic University -- Dissertations
Department: Dept. of Computing
Pages: 1 v. (various pagings) : ill. ; 30 cm
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b1235031
URI: http://theses.lib.polyu.edu.hk/handle/200/4576
Abstract: Orphan policy reallocation process is a complex process for policy assignment to inforce agent. In this research project, I focus on the development of an Expert System for Reallocation of Orphan Policies for individual life insurance in an insurance company. It involves the requirement analysis, design and implementation of the Expert System. The KADS development approach is adopted in the research. It is a structural approach to assist Expert System developer to obtain the system requirement and knowledge base in a formal way and generating different kinds of models in the course of Expert System development. There are different phases in this research project. They are analysis phase, design phase, implementation phase and test and evaluation phases based upon KADS approach for the development of Expert System. The KAPPA-PC expert system shell and database concepts are adopted for integrating the Expert System with the database system. It facilitates ease of maintenance in the future. Therefore, all Expert System solution and knowledge base are kept in database records. The IS manager/knowledge engineer can manipulate the knowledge base easily without working on the Expert System platform. The Expert System is window-based and all functions are icon-driven. The user interface design is based on the Windows standard. It can provide fancy outlook of the screen output and facilitate ergonomics concept on the design of user interface in this Expert System. The major output of the Expert System is to allocate right inforce agent to handle particular orphan policies. There are many criteria set in the System for carrying out inference to assess inforce agents. The result of assessment is the overall certainty factor of the agent. In turn, the Expert System allows users to input their user defined criteria to carry out second matching with the agent records. Finally, the System provides top three right inforce agents with the highest certainty factor incorporated with explanation of agent details for user to confirm which agent is suitable for particular orphan policy. After the development of the Expert System, I have also carried out test and evaluation of the System. Two testing techniques have been adopted. There are black box testing technique and user acceptance test technique. The result of evaluation is acceptable as the effectiveness of the Expert System is ranging from 90% to 100%. In this research project, I study in depth of the applications of expert systems in insurance industry and explore the opportunity of developing an expert system for orphan policy reallocation in an insurance company.

Files in this item

Files Size Format
b1235031x.pdf 8.286Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. 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.
  3. 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.

     

Quick Search

Browse

More Information