![]() | Only 14 pages are availabe for public view |
Abstract This thesis presents an intelligent knowledge discovery (KDD) approach for insurance companies databases. The proposed approach introduced the design and implementation of a life insurance target DB for data analysis purposes, data warehouses, OLAP operations and data mining models. The proposed approach is able to discover the hidden data relationships, patterns, data attribute dependencies, and rules, in the major insurance companies DBs in Egypt. It provides a valuable knowledge supporting the life insurance manager in taking decisions concerning the acceptance of an applicant for life insurance, and the underwriting process. In addition, the proposed KDD approach is able to perform customers segmentation to determine different life insured clusters according to their data attributes such as age, profession, monthly income value, insured city, insurance sum, etc. it is highly recommended that the proposed intelligent KDD approach in this thesis and all the derived knowledge from implementing the proposed approach, should be applied in Egyptian insurance companies, and applying it on other important domains such as medicine, credit assessment in banks, stock markets, and investment assessment, after making the appropriate tuning to the model to accommodate the conditions of the domain to be applied on. |