Actuarial Science and Artificial Intelligence: Optimization and Deep Learning for Risk Modeling in Morocco 2022
ABSTRACT: This study explores the integration of actuarial science and artificial intelligence through a hybrid framework combining optimization techniques and deep learning to enhance actuarial risk modeling. Using a Moroccan case study, we leverage linear programming for financial decision-making and arti- ficial neural networks (ANN) for predicting and analyzing actuarial risks under uncertainty. The methodology is applied to real-world data from the Moroccan insurance sector, demonstrating its practical relevance for improving long-term financial planning and risk evaluation. Experimental results show that the ANN model achieves a normali
Resource information
- Authors
- Hamza Boucheta, Marouane Karim, Agouram El Mahjoub, Noura Moummadi, Lamia Mourtadi, Faris Asmaa, Elhachloufi Mostafa
- Research area
- Artificial intelligence
- Research topics
- automobile insurance, premium pricing, generalized linear models (GLM), credibility theory, risk dis
- Publication date
- 2025
- DOI
- 10.5281/zenodo.17175611
- Upstream last modified
- Sep 22, 2025
- License
- Creative Commons Attribution 4.0 International
- Last record update
- Nov 5, 2026
About this resource
ABSTRACT: This study explores the integration of actuarial science and artificial intelligence through a hybrid framework combining optimization techniques and deep learning to enhance actuarial risk modeling. Using a Moroccan case study, we leverage linear programming for financial decision-making and arti- ficial neural networks (ANN) for predicting and analyzing actuarial risks under uncertainty. The methodology is applied to real-world data from the Moroccan insurance sector, demonstrating its practical relevance for improving long-term financial planning and risk evaluation. Experimental results show that the ANN model achieves a normalized Mean Absolute Error (MAE) of 0.625, outperforming traditional Generalized Linear Models (GLMs) by approximately 15% in pre- dictive accuracy. Risk assessment metrics further reveal improvements, with the 95% Value at Risk (VaR) and Tail Value at Risk (TVaR) reduced by 9.4% and 13.9%, respectively, compared to Poisson and Negative Binomial GLMs. These gains highlight the ANN’s capacity to capture complex nonlinear relationships and heteroscedasticity in insurance claim data. Moreover, linear programming integration enables optimized premium pricing and reserve allocation under multiple regulatory and economic constraints. This hybrid approach fosters a more robust and adaptive actuarial process, equipping insurers to bet- ter manage uncertainty and extreme risk scenarios. Overall, this work modernizes actuarial practices by introducing intelligent, data-driven models that enhance predictive performance and strategic decision-making, contributing to sustainable financial stability in emerging markets such as Morocco.