Journal Article

ResPoNet: A Residual Neural Network for Efficient Valuation of Large Variable Annuity Portfolios

Xu, Jie, Mamon, Rogemar, Zhao, Yixing, Xiong, Heng

2025

Overview

Accurately valuing large portfolios of Variable Annuities (VAs) poses a significant challenge due to the high computational burden of Monte Carlo simulations and the limitations of spatial interpolation methods that rely on manually defined distance metrics. We introduce a residual portfolio valuation network (ResPoNet), a novel residual neural network architecture enhanced with weighted loss functions, designed to improve valuation accuracy and scalability. ResPoNet systematically accounts for mortality risk and path-dependent liabilities using residual layers, while the custom loss function ensures better convergence and interpretability. Numerical results on synthetic portfolios of 100,000 contracts show that ResPoNet achieves significantly lower valuation errors than baseline neural and spatial methods, with faster convergence and improved generalization. Sensitivity analysis reveals key drivers of performance, including guarantee complexity and contract maturity, demonstrating the robustness and practical applicability of ResPoNet in large-scale VA valuation.

• Publisher: MDPI AG
• Subject: Artificial neural networks / Convergence / Insurance premiums / Investment analysis / Life insurance / Machine learning / Methods / Monte Carlo method / Monte Carlo simulation / neural network / Neural networks / Policyholders / Portfolio management / portfolio valuation / Securities markets / Sensitivity analysis / Simulation / Valuation / Variable annuities / variable annuity