Chapter 37 Developing a Rule Base for Recommending Insurance Products

摘要

This paper presents a fuzzy rule base for insurance prospects profiling based on two main sources, i.e. from dataset and experts. A historical dataset of Islamic insurance policyholders was used as a case study for this purpose. The Wang and Mendel algorithm (WMA) (Wang and Mendel, IEEE Trans Syst Man Cybern 22:1414-1472) was applied on the dataset to generate fuzzy rules which includes five types of policies with five pre-determined most influential variables, namely age, gender, marital status, monthly salary and job class. Fuzzy rules from the dataset and expert were compared based on similarity and accuracy measures. The rule base is proposed to be used by insurance advisors to make decisions and provide appropriate proposals according to the prospect's profile.