Ruswandi, Rudi and Nuryaman, Aang and Saidi, Subian (2019) Analysis of The Aggregation Claim Number Distributed Poisson with Amount of Claims Distributed Gamma and Rayleigh. In: The 6th International Conference on Mathematics, Science and Education (ICMSE), 9-10 Oktober 2019, Semarang. (Unpublished)

Text ICMSE_Aang.docx Download (194kB)

Abstract

A claim is a transfer of risk from the insured to the guarantor. Claims that occur individually are called individual claims, whereas collections of individual claims are called aggregation claims in a single period of vehicle insurance. Aggregation claims consist of a pattern of the number and amount (nominal value) of individual claims, so that the model of aggregation claims is formed from each distribution of the number and amount of claims. The distribution of claims is based on the probability density function and the cumulative density function. One method that can be used to obtain a claim aggregation model is to use convolution, which is by combining the distribution of the number of claims and the distribution of the amount of claims so that the expected value can be obtained to predict the value of pure premiums. In this paper, aggregation claim modeling will be carried out with the number of claims distributed Poisson and the amount of claims distributed Gamma. As comparison, we compare it with claim amount distributed Rayleigh. By using VaR (value at risk) and MSE (Mean Square Error) indicators, the results of the analysis show that the Rayleigh distribution is better used for distributing data that has extreme values. Data analysis in this study was conducted using the R program package.

Item Type:	Conference or Workshop Item (Speech)
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Fakultas Matematika dan Ilmu Pengetahuan Alam (FMIPA) > Prodi Matematika
Depositing User:	Mr. Aang Nuryaman
Date Deposited:	04 Nov 2019 08:26
Last Modified:	04 Nov 2019 08:26
URI:	http://repository.lppm.unila.ac.id/id/eprint/14888

Actions (login required)

View Item