Insurance Claim Budget Efficiency Based on Customer Lifestyle Risk Profile
International Journal of Applied Artificial Intelligence and Robotics · 16.10.2026 · 2 (2) · 25-32
DOI: 10.67745/ijaic.v2i2.23 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Applied Artificial Intelligence and Robotics, online erschienen am 16.10.2026. Verfasst von Khalil Putra Pratama und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Pratama, K. P., & Pamungkas, R. W. P. (2026). Insurance Claim Budget Efficiency Based on Customer Lifestyle Risk Profile. International Journal of Applied Artificial Intelligence and Robotics, 2(2), 25-32. https://doi.org/10.67745/ijaic.v2i2.23
Vancouver
Pratama KP, Pamungkas RWP. Insurance Claim Budget Efficiency Based on Customer Lifestyle Risk Profile. International Journal of Applied Artificial Intelligence and Robotics. 2026;2(2):25-32. doi:10.67745/ijaic.v2i2.23
BibTeX
@article{Pratama2026,
author = {Pratama, Khalil Putra and Pamungkas, R Wisnu P},
title = {Insurance Claim Budget Efficiency Based on Customer Lifestyle Risk Profile},
journal = {International Journal of Applied Artificial Intelligence and Robotics},
year = {2026},
volume = {2},
number = {2},
pages = {25--32},
doi = {10.67745/ijaic.v2i2.23}
}
EUVIMED