Vol. 2 No. 2 (2026): Vol 2 No 2 (November 2026)
Articles

Insurance Claim Budget Efficiency Based on Customer Lifestyle Risk Profile

PDF
  • Khalil Putra Pratama,
  • R Wisnu P Pamungkas
Khalil Putra Pratama
Universitas Bhayangkara Jakarta Raya
R Wisnu P Pamungkas
Universitas Bhayangkara Jakarta Raya

Published 16-10-2026

Keywords

  • claim budget efficiency,
  • lifestyle risk profiling,
  • logistic regression,
  • Cramer's V,
  • synthetic data

Copyright (c) 2026 Khalil Putra Pratama, R Wisnu P Pamungkas (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Abstract

Insurance companies commonly allocate claim reserve budgets by customer location, assuming policyholders in the same region share similar risk. This study tests that assumption and demonstrates a complementary risk-scoring framework using a public, synthetic health-insurance dataset of 30,000 customers across 11 districts of Bekasi City, Indonesia, obtained from Kaggle. Chi-square tests and Cramer's V effect sizes were computed for ten categorical variables against claim outcome, followed by logistic regression and random forest models combining nine lifestyle variables to predict claim outcome, excluding location. Location was not statistically significant (Cramer's V = 0.019, p = 0.366), while lifestyle variables showed strong associations, led by smoking status (V = 0.767, p < 0.001). Both the logistic regression and random forest models achieved an identical held-out test AUC of 0.993, separating customers into low- (44.3%), medium- (24.2%), and high-risk (31.5%) tiers with claim rates of 0.0%, 67.6%, and 100.0%. This near-perfect, model-agnostic separation, together with several counter-intuitive associations for smoking and exercise frequency, indicates the dataset's claim label likely follows a synthetic generation rule rather than real-world claims noise; both observations are discussed as evidence of the dataset's synthetic nature rather than as generalizable clinical findings. A simulated budget reallocation illustrates how reserves could shift from a non-claiming low-risk segment toward a high-risk segment without increasing total budget. The study's contribution is a statistically grounded, replicable analytical framework for individual risk-score-based claim reserve budgeting, which should be validated on real, audited insurance data before operational use.

PDF

Downloads

Download data is not yet available.

References

  1. K. Kaushik, A. Bhardwaj, A. D. Dwivedi, and R. Singh, "Machine Learning-Based Regression Framework to Predict Health Insurance Premiums," Int. J. Environ. Res. Public Health, vol. 19, no. 13, art. 7898, 2022, doi: 10.3390/ijerph19137898.
  2. A. Alam and V. R. Prybutok, "Use of responsible artificial intelligence to predict health insurance claims in the USA using machine learning algorithms," Explor. Digit. Health Technol., vol. 2, pp. 30-45, 2024, doi: 10.37349/edht.2024.00009.
  3. M. Johnson, A. Albizri, and A. Harfouche, "Responsible artificial intelligence in healthcare: predicting and preventing insurance claim denials for economic and social wellbeing," Inf. Syst. Front., 2021, doi: 10.1007/s10796-021-10137-5.
  4. U. Orji and E. Ukwandu, "Machine learning for an explainable cost prediction of medical insurance," arXiv preprint, arXiv:2311.14139, 2023.
  5. W.-C. Lo, T.-H. Hu, C.-Y. Shih, H.-H. Lin, and J.-S. Hwang, "Impact of healthy lifestyle factors on life expectancy and lifetime health care expenditure: nationwide cohort study," JMIR Public Health Surveill., 2024, PMID: 39018094.
  6. H.-J. Li, X.-G. Luo, Z.-L. Zhang, S.-W. Huang, and W. Jiang, "A usage-based insurance (UBI) pricing model considering customer retention," Insurance Math. Econ., 2025, in press, doi: 10.1016/j.insmatheco.2025.06.006.
  7. M. Mayadi, R. W. P. Pamungkas, A. Azlan, K. Khairunnisa, and F. T. Waruwu, "Analisis Sistem Pendukung Keputusan Penentuan Kasi Terbaik Menerapkan Metode OCRA dengan Pembobotan Rank Order Centroid (ROC)," Build. Informatics Technol. Sci. (BITS), vol. 3, no. 3, pp. 393-399, 2021, doi: 10.47065/bits.v3i3.1100.
  8. B. Langenberger, T. Schulte, and O. Groene, "The application of machine learning to predict high-cost patients: a performance-comparison of different models using healthcare claims data," PLOS ONE, vol. 18, no. 1, art. e0279540, 2023, doi: 10.1371/journal.pone.0279540.
  9. M. Denuit, A. Charpentier, and J. Trufin, "Autocalibration and Tweedie-dominance for insurance pricing with machine learning," Insurance Math. Econ., vol. 101, pp. 485-497, 2021, doi: 10.1016/j.insmatheco.2021.08.010.
  10. S. Devriendt, K. Antonio, T. Reynkens, and R. Verbelen, "Sparse regression with multi-type regularized feature modeling," Insurance Math. Econ., vol. 96, pp. 248-261, 2021, doi: 10.1016/j.insmatheco.2020.11.010.
  11. H. Cramér, Mathematical Methods of Statistics. Princeton, NJ, USA: Princeton Univ. Press, 1946.
  12. D. W. Hosmer, S. Lemeshow, and R. X. Sturdivant, Applied Logistic Regression, 3rd ed. Hoboken, NJ, USA: Wiley, 2013.
  13. L. Breiman, "Random forests," Mach. Learn., vol. 45, no. 1, pp. 5-32, 2001, doi: 10.1023/A:1010933404324.
  14. T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD), 2016, pp. 785-794, doi: 10.1145/2939672.2939785.
  15. A. Agresti, Statistical Methods for the Social Sciences, 5th ed. Boston, MA, USA: Pearson, 2018.
  16. T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. New York, NY, USA: Springer, 2009.
  17. D. Rankin, M. Black, R. Bond, J. Wallace, M. Mulvenna, and G. Epelde, "Reliability of supervised machine learning using synthetic data in health care: model to preserve privacy for data sharing," JMIR Med. Inform., vol. 8, no. 7, art. e18910, 2020, doi: 10.2196/18910.
  18. S. Uddin and H. Lu, "Dataset meta-level and statistical features affect machine learning performance," Sci. Rep., vol. 14, art. 1670, 2024, doi: 10.1038/s41598-024-51825-x.
  19. M. Michaelides, M. Pigeon, and H. Cossette, "Individual claims reserving using activation patterns," Eur. Actuarial J., 2023, doi: 10.1007/s13385-023-00355-3.
  20. S. Shaham, G. Ghinita, and C. Shahabi, "Models and mechanisms for spatial data fairness," Proc. VLDB Endow., vol. 16, no. 4, pp. 1014-1027, 2022, doi: 10.14778/3565816.3565820.
  21. B. Wijaya and R. W. P. Pamungkas, "IT governance and capacity building for smart city development," J. Int. Multidiscip. Res., vol. 3, no. 1, pp. 268-275, 2025.
  22. R. W. P. Pamungkas and K. Rakhmi, "Monitoring sebaran petugas lapangan Citarum Harum dalam pelaporan digital," J. Ilmiah Sist. Inf. dan Tek. Inform., vol. 9, no. 1, pp. 71-81, 2019.
  23. S. M. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," in Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 30, 2017, pp. 4765-4774.
  24. K. Pearson, "On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling," Philos. Mag., Ser. 5, vol. 50, no. 302, pp. 157-175, 1900, doi: 10.1080/14786440009463897.
  25. G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning: with Applications in R, 2nd ed. New York, NY, USA: Springer, 2021.