Estimasi Cadangan Klaim Individu untuk Klaim Short-Tailed dan Long-Tailed Menggunakan Algoritma Backpropagation

Anas Satriya Rabdika; Azizah Azizah

doi:10.37905/jjom.v8i1.35114

Estimasi Cadangan Klaim Individu untuk Klaim Short-Tailed dan Long-Tailed Menggunakan Algoritma Backpropagation

Anas Satriya Rabdika, Azizah Azizah

Abstract

In insurance, risk can occur at any time, causing claims to sometimes have a large amount of value, so that insurance companies may not be able to satisfy claim payments. If these situations occur, insurance companies need claim reserves to prepare for such events. There are several methods to calculate claim reserves, such as aggregate claim reserving. However, certain claim characteristics involve dependencies among claims, which result in a lack of detailed information for individual claims. In addition, an increasing number of claims becomes more difficult to compute using traditional methods. Therefore, this research aims to calculate individual claim reserves using one branch of machine learning, namely the Backpropagation Algorithm. The Backpropagation Algorithm is believed to remain relevant compared to other algorithmic models because, in several studies, it produces relatively low values of Mean Absolute Percentage Error (MAPE), at approximately 2.70%. The data used in this research are simulated using R software, generating 10,000 claims over 20 years, consisting of 6,000 short-tailed claims and 4,000 long-tailed claims. The data model is evaluated using MAPE. The resulting MAPE value is 0.55%, indicating that the data are highly suitable for predictive modeling. The prediction results show that the total claims to be paid in the 21st development year reach Rp22,945,450,000,000, with an average claim amount of approximately Rp2,294,545,152. This research contributes to both informatics and actuarial science by developing an individual claim reserving approach to predict claim payments more efficiently.

Keywords

Backpropagation Algorithm; Individual claim reserving; Machine learning; Short-tailed claims; Long-tailed claims

Full Text:

PDF

References

A. N. Mandia, J. K. Mungatu, and P. G. O. Weke, “Measuring multivariate negative dependence in higher dimensions using copula-based approach,” Universal Journal of Applied Mathematics, vol. 12, no. 2, pp. 50–61, Apr. 2024, doi: 10.13189/ujam.2024.120202.

S. Srun, T. Kean, C. Khim, M. S. Rakitina, I. A. Dmitrieva, and N. A. Ivanova, “Evaluation of claims reserve methods: Claims payment pattern and standard Bühlmann, case study at Prévoir Insurance Company (Agriculture Cambodia),” E3S Web of Conferences, vol. 486, p. 03015, 2024, doi: 10.1051/e3sconf/202448603015.

S. C. Vanegas, A. L. Bădescu, and X. S. Lin, “Claim reserving via inverse probability weighting: A micro-level chain-ladder method,” European Actuarial Journal, vol. 15, no. 1, pp. 89–135, Apr. 2025, doi: 10.1007/s13385-024-00395-3.

I. Chaoubi, C. Besse, H. Cossette, and M. Côté, “Micro-level reserving for general insurance claims using a long short-term memory network,” Applied Stochastic Models in Business and Industry, vol. 39, no. 3, pp. 382–407, May 2023, doi: 10.1002/asmb.2750.

H. Abdelrahman, A. Bădescu, R. Craiu, and S. Lin, “Marked Cox models for IBNR claims count: Continuous and discretized approaches with Dirichlet-driven reporting delays,” arXiv, Sep. 2024, doi: 10.48550/arXiv.2409.12896.

H. Surden, “Machine learning and law: An overview,” in Research Handbook on Big Data Law, R. Vogl, Ed. Cheltenham, U.K.: Edward Elgar Publishing, 2021, doi: 10.4337/9781788972826.00014.

Ł. DeLóng, M. Lindholm, and M. V. Wüthrich, “Collective reserving using individual claims data,” Scandinavian Actuarial Journal, vol. 2022, no. 1, pp. 1–28, Jan. 2022, doi: 10.1080/03461238.2021.1921836.

M. V. Wüthrich, “Machine learning in individual claims reserving,” Scandinavian Actuarial Journal, vol. 2018, no. 6, pp. 465–480, Jul. 2018, doi: 10.1080/03461238.2018.1428681.

S. T. Hassan, Parvin, Asha, A. Datta, and S. Mondal, “Use of machine learning classifiers on structured vs. unstructured data,” International Journal of Scientific Research in Engineering and Management, vol. 8, no. 3, pp. 1–5, Mar. 2024, doi: 10.55041/IJSREM29771.

S. Syaharuddin, F. Fatmawati, and H. Suprajitno, “Best architecture recommendations of ANN backpropagation based on combination of learning rate, momentum, and number of hidden layers,” Jurnal Teknik Aplikasi Matematika, vol. 6, no. 3, p. 629, Jul. 2022, doi: 10.31764/jtam.v6i3.8524.

E. Bravo-López, T. Fernández Del Castillo, C. Sellers, and J. Delgado-García, “Landslide susceptibility mapping with artificial neural networks: Multi-approach analysis of backpropagation algorithm applying the NeuralNet package in Cuenca, Ecuador,” Remote Sensing, vol. 14, no. 14, p. 3495, Jul. 2022, doi: 10.3390/rs14143495.

G. G. Tolun and Y. A. Kaplan, “Development of backpropagation algorithm for estimating solar radiation: A case study in Turkey,” Renewable and Sustainable Technologies – Electrical Engineering, vol. 68, no. 3, pp. 313–316, Oct. 2023, doi: 10.59277/RRST-EE.2023.3.11.

J. M. Ahuja, M. Sharma, and V. Birchha, “Solar energy prediction using LM backpropagation in ANN,” IOSR Journal of Computer Engineering, vol. 21, no. 1, pp. 1–7, 2019.

M. Li, “Comprehensive review of backpropagation neural networks,” Asian Journal of Science and Technology, vol. 9, no. 1, pp. 150–154, Jan. 2024, doi: 10.54097/51y16r47.

M. Hofert, “The philosophy of copula modeling: A conversation with ChatGPT,” Journal of Data Science, vol. 21, no. 4, pp. 619–637, 2023, doi: 10.6339/23-JDS1114.

M. G. Cruz, G. W. Peters, and P. V. Shevchenko, Fundamental Aspects of Operational Risk and Insurance Analytics: A Handbook of Operational Risk. Hoboken, NJ, USA: John Wiley & Sons, 2015.

I. M. Widiartha, A. A. N. Gunawan, E. R. N. A. Sanjaya, and K. Sari, “A hybrid method of backpropagation and particle swarm optimization for enhancing accuracy performance,” Current Journal of Applied Science and Technology, vol. 42, no. 6, pp. 10–18, Mar. 2023, doi: 10.9734/cjast/2023/v42i64072.

K. Markov, “Multilayer perceptron with backpropagation, HDL coder, and FPGA technology: An integrated approach for efficient neural network implementation,” Problems of Engineering Cybernetics and Robotics, vol. 80, Dec. 2023, doi: 10.7546/PECR.80.23.02.

A. Apicella, F. Isgrò, and R. Prevete, “Hidden classification layers: Enhancing linear separability between classes in neural network layers,” Pattern Recognition Letters, vol. 177, pp. 69–74, Jan. 2024, doi: 10.1016/j.patrec.2023.11.016.

D. Qiu, “Individual claims reserving: Using machine learning methods,” M.S. thesis, Concordia University, Montreal, QC, Canada, Dec. 2019. [Online]. Available: https://spectrum.library.concordia.ca/id/eprint/986258/

Mukhaiyar et al., “The value at risk analysis using heavy-tailed distribution on the insurance claims data,” Jurnal Teknik Aplikasi Matematika, vol. 8, no. 4, p. 1233, Oct. 2024, doi: 10.31764/jtam.v8i4.25053.

Asosiasi Asuransi Umum Indonesia, Asuransi Umum dan Reasuransi Tahun 2022 (Unaudited), Mar. 2023.

B. Konda, “The impact of data preprocessing on data mining outcomes,” World Journal of Advanced Research and Reviews, vol. 15, no. 3, pp. 540–544, Sep. 2022, doi: 10.30574/wjarr.2022.15.3.0931.

D. Chicco, L. Oneto, and E. Tavazzi, “Eleven quick tips for data cleaning and feature engineering,” PLoS Computational Biology, vol. 18, no. 12, p. e1010718, Dec. 2022, doi: 10.1371/journal.pcbi.1010718.

I. Izonin, R. Tkachenko, N. Shakhovska, B. Ilchyshyn, and K. K. Singh, “A two-step data normalization approach for improving classification accuracy in the medical diagnosis domain,” Mathematics, vol. 10, no. 11, p. 1942, Jun. 2022, doi: 10.3390/math10111942.

D. Marlina and F. Arifin, “Predicting the number of tourists based on backpropagation algorithm,” Jurnal RESTI, vol. 5, no. 3, pp. 439–445, Jun. 2021, doi: 10.29207/resti.v5i3.3061.

A. P. Windarto, “Implementasi JST dalam menentukan kelayakan nasabah pinjaman KUR pada Bank Mandiri Mikro Serbelawan dengan metode backpropagation,” J-SAKTI, vol. 1, no. 1, pp. 12–23, Aug. 2017, doi: 10.30645/jsakti.v1i1.25.

A. B. Pratama, “Rainfall forecasting in Lampung Province using backpropagation neural network,” B.S. thesis, Universitas Lampung, Bandar Lampung, Indonesia, 2023.

F. Khairati and H. Putra, “Prediksi kuantitas penggunaan obat pada layanan kesehatan menggunakan algoritma backpropagation neural network,” JSISFOTEK, pp. 128–135, Aug. 2022, doi: 10.37034/jsisfotek.v4i3.158.

V. Shatravin, D. Shashev, and S. Shidlovskiy, “Sigmoid activation implementation for neural networks hardware accelerators based on reconfigurable computing environments for low-power intelligent systems,” Applied Sciences, vol. 12, p. 5216, May 2022, doi: 10.3390/app12105216.

R. G. Santosa, A. R. Chrismanto, Y. Lukito, and W. S. Raharjo, “The MAPE analysis of ARIMA (p,d,q) on LQ45 stock price to determine training data period,” International Journal of Information Technology and Computer Science Applications, vol. 2, no. 3, pp. 182–201, Dec. 2024, doi: 10.58776/ijitcsa.v2i3.168.

I. Nabillah and I. Ranggadara, “Mean absolute percentage error untuk evaluasi hasil prediksi komoditas laut,” Journal of Information Systems, vol. 5, no. 2, pp. 250–255, Nov. 2020, doi: 10.33633/joins.v5i2.3900.

N. Susyanto and J. P. Arcede, “Unveiling SIR model parameters: Empirical parameter approach for explicit estimation and confidence interval construction,” Jambura Journal of Biometrics, vol. 5, no. 1, pp. 54–62, Jul. 2024, doi: 10.37905/jjbm.v5i1.26287.

D. Rodin et al., “An accurate wearable hydration sensor: Real-world evaluation of practical use,” PLoS ONE, vol. 17, no. 8, p. e0272646, Aug. 2022, doi: 10.1371/journal.pone.0272646.

DOI: https://doi.org/10.37905/jjom.v8i1.35114