مجلة افاق علوم الادارة والاقتصاد
Volume 10, Numéro 1, Pages 302-317
2026-07-30

A Hybrid Deep Learning Model For Systemic Insurance Risk Prediction: Integrating Climate Catastrophe And Telematics Data

Authors : Hamel Dalila . Djafri Asma .

Abstract

In response to the growing challenges posed by climate-related catastrophes and dynamic policyholder behaviors, this study develops a hybrid deep learning framework combining Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Explainable AI (XAI) techniques. Using multi-modal data streams from satellite climate indices, telematics driving patterns, and insurance claims, the model outperforms traditional actuarial methods with a 15–22% improvement in predictive accuracy. The integration of SHAP-based interpretability ensures compliance with regulatory transparency requirements. Results demonstrate the framework’s potential for adaptive underwriting, catastrophe pooling, and proactive systemic risk management in the insurance sector.

Keywords

Systemic Risk; . ; Deep Learning; Insurance Analytics; ; Telematics; . ; Climate Catastrophes; Explainable AI.