Sensitivity of Premium Calculations to Distribution Assumptions: The Impact of Using Pareto vs. Pareto Distributions Exponential on Claims of Large Losses

aisha hadiat; Niken Pinkyvita Nur Anjani

doi:10.47194/ijgor.v6i4.409

Authors

aisha hadiat
aisha22003@mail.unpad.ac.id
Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Padjadjaran, Bandung
Niken Pinkyvita Nur Anjani Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Padjadjaran, Bandung

Keywords:

insurance premiums, Pareto distribution, exponential distribution, large claims, model sensitivity, risk management

Abstract

Premium calculation is a fundamental aspect of the insurance industry to ensure the sustainability and profitability of companies. One of the main factors that affect the accuracy of premium calculation is the selection of claim probability distribution, especially for large claims that have the potential to cause significant losses. Exponential distribution is often used because of its simplicity, but its light tail characteristic makes it less suitable for modeling extreme claims. Conversely, the Pareto distribution, with its heavy-tailed nature, is considered more representative in capturing the risk of large claims. This study aims to analyze the sensitivity of premium calculations to distribution assumptions by comparing the use of exponential and Pareto distributions on large loss claim data. This analysis is expected to provide a practical overview of the impact of distribution selection on premium setting and its implications for insurance risk management in Indonesia.

References

Alfaridzi, S. I. R., & Prabowo, A. (2023). Determination of premium rates for vehicle insurance with claim size following exponential and gamma distributions. Premium Insurance Business Journal, 10(1), 29–41. http://ejournal.stma-trisakti.ac.id/index.php/premium/article/view/46

Alfaridzi, S. I. R., & Prabowo, A. (2023). Penentuan tarif premi pada asuransi kendaraan dengan besar klaim berdistribusi eksponensial dan gamma. Premium Insurance Business Journal, 10(1), 29–41. http://ejournal.stma-trisakti.ac.id/index.php/premium/article/view/46

Alfaridzi, S. I. R., & Prabowo, A. (2024). Calculating optimal traffic accident insurance premiums based on claim size and claim frequency. Lamda: Scientific Journal of MIPA Education and its Application. https://ejournal.baleliterasi.org/index.php/lambda/article/view/843

Alfaridzi, S. I. R., & Prabowo, A. (2024). Menghitung premi asuransi kecelakaan lalu lintas yang optimal berdasarkan besar klaim dan frekuensi klaim. Lamda: Jurnal Ilmiah Pendidikan MIPA dan Aplikasinya. https://ejournal.baleliterasi.org/index.php/lambda/article/view/843

Bowers, N. L., Gerber, H. U., Hickman, J. C., Jones, D. A., & Nesbitt, C. J. (1997). Actuarial Mathematics (2nd ed.). Society of Actuaries.

Chavez-Demoulin, V., Embrechts, P., & Hofert, M. (2016). An extreme value approach for modeling operational risk losses depending on covariates. Journal of Risk and Insurance, 83(3), 735–776. https://doi.org/10.1111/jori.12070

Cooray, K., & Ananda, M. M. A. (2005). Modeling actuarial data with a composite lognormal–Pareto model. Scandinavian Actuarial Journal, 2005(5), 321–334. https://doi.org/10.1080/03461230510009719

Diba, F., Saepudin, D., & Rohmawati, A. A. (2017). Modeling and simulation of the probability of bankruptcy of insurance companies with analysis of premium value and claim size assumed to be exponentially distributed. Indonesian Journal on Computing (Indo-JC), 2(2), 1–10. https://socjs.telkomuniversity.ac.id/ojs/index.php/indojc/article/view/147

Diba, F., Saepudin, D., & Rohmawati, A. A. (2017). Pemodelan dan simulasi peluang kebangkrutan perusahaan asuransi dengan analisis nilai premi dan ukuran klaim diasumsikan berdistribusi eksponensial. Indonesian Journal on Computing (Indo-JC), 2(2), 1–10. https://socjs.telkomuniversity.ac.id/ojs/index.php/indojc/article/view/147

Embrechts, P., Klüppelberg, C., & Mikosch, T. (1997). Modelling extremal events for insurance and finance. Springer.

Mao, T., Hu, T., & Hu, Z. (2015). On risk measures for heavy-tailed losses under insurance and finance. ASTIN Bulletin, 45(2), 425–452. https://doi.org/10.1017/asb.2014.30

Note: The APA format is preserved. Indonesian titles and journal names are translated for context.

Putra, T. A. J., Lesmana, D. C., & Purnaba, I. G. P. (2021). Calculation of motor vehicle insurance premiums using generalized linear models with a Tweedie distribution. Jambura Journal of Mathematics. https://ejurnal.ung.ac.id/index.php/jjom/article/view/10136

Putra, T. A. J., Lesmana, D. C., & Purnaba, I. G. P. (2021). Penghitungan premi asuransi kendaraan bermotor menggunakan generalized linear models dengan distribusi Tweedie. Jambura Journal of Mathematics. https://ejurnal.ung.ac.id/index.php/jjom/article/view/10136

Resnick, S. I. (2007). Heavy-Tail Phenomena: Probabilistic and Statistical Modeling. Springer.