Predicting Individual Ultimate Claim Amounts with Hybrid Neural Networks and Claim Segmentation: A Benchmark for Microlevel Loss Reserving
Mathematics · 19.11.2026 · 14 (22) · 4258
DOI: 10.3390/math14224258 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 19.11.2026. Verfasst von Re-Mi Hage und 2 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Microlevel loss reserving can use claim-level information that aggregate methods such as chain ladder cannot exploit. This paper predicts individual ultimate claim amounts with a hybrid neural network that combines a feedforward network for static claim characteristics with a long short-term memory network for the payment history of each claim. The framework is evaluated on a simulated motor-insurance portfolio of claims closed at the final valuation date, so that predictions can be compared with known ultimates; the estimation of RBNS and IBNR reserves is outside the scope of the study. Severity strata are formed by k-means clustering of the ultimate amount, and covariates are selected with the Boruta algorithm, both fitted to the training claims only. With complete payment histories, the hybrid models produce much smaller aggregate deviations than chain ladder for recent accident years, while chain ladder remains competitive for mature ones. Boruta retains one or two covariates; the reduced set helps only the untuned full-portfolio model, whereas in the tuned severity-stratum models the full covariate set lowers the test MAE by one third to one half. In a backtest with payment histories truncated at December 2019, the hybrid models keep an accident-year MAPE of 2.1–3.0%, against 16.5% for chain ladder, but improve on the amount paid to date by only 10–15% for claims still open at that date. The results indicate that feature selection, segmentation, and model tuning should be evaluated jointly.
Zitieren
APA
Hage, R., Badran, R., & Aramouny, S. (2026). Predicting Individual Ultimate Claim Amounts with Hybrid Neural Networks and Claim Segmentation: A Benchmark for Microlevel Loss Reserving. Mathematics, 14(22), 4258. https://doi.org/10.3390/math14224258
Vancouver
Hage R, Badran R, Aramouny S. Predicting Individual Ultimate Claim Amounts with Hybrid Neural Networks and Claim Segmentation: A Benchmark for Microlevel Loss Reserving. Mathematics. 2026;14(22):4258. doi:10.3390/math14224258
BibTeX
@article{Hage2026,
author = {Hage, Re-Mi and Badran, Rabih and Aramouny, Sarah},
title = {Predicting Individual Ultimate Claim Amounts with Hybrid Neural Networks and Claim Segmentation: A Benchmark for Microlevel Loss Reserving},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {22},
pages = {4258},
doi = {10.3390/math14224258}
}
EUVIMED