Fuzzy Based Decision Support Model for Health Insurance Claim

Abstract

Insurance industry in Indonesia has shown promising result based on premium growth in 2014-2018, as recorded in Indonesia General Insurance Market Update 2019. With the increase of premium, the claim rate also grows. Insurance companies face challenges in processing the claims. Many factors need to be carefully considered before making a claim decision. This paper proposes a decision support model (DSM) to score claim cases and to propose claim risk category (CRC) and claim decision (CD). The model was built with 13 parameters, divided into non-fuzzy group and fuzzy group. The analytic hierarchy process (AHP) method was used to determine the priority weight (PW) among parameters. The Tsukamoto’s fuzzy logic (FL) method was applied to process the fuzzy parameters. A simple mathematics method (SMM) was exercised to calculate the non-fuzzy parameters, and to aggregate the result into claim risk score (CRS). Finally, CRC and CD were derived from the CRS using a rule base. The model was tested using 19611 actual claim history records. The result was: 6171 (31.47%) accepted with CRC= low, 3459 (17.64%) pending (CRC medium), and 9981 (50.89%) pending (CRC high). The DSM model was implemented in python with Google COLAB and Datapane to create various graphics.