FAM seminar: Optimizing Portfolios with Surrender Variable Annuities: A Deep Reinforcement Learning Approach

Details

Date: Friday, 11 April, 2025

Time: 3:30-4:30 pm

Venue: MB 441

Speaker: Ms. Huifang Huang, Huazhong University of Science and Technology

Topic: Optimizing Portfolios with Surrender Variable Annuities: A Deep Reinforcement Learning Approach

Abstract

This paper investigates a portfolio optimization problem for an investor on asset allocation among risk-free asset, risky asset, and variable annuities with guaranteed minimum death benefits (GMDB) subject to mortality risk and surrender risk. The investor’s objective is to maximize the expected utility of the bequest at death or the expected utility of assets at contract maturity. On each trading day before the investor’s death, the investor can adjust the allocation between risk-free and risky assets, invest in new surrender GMDB product, or partially or fully surrender existing annuities. This dynamic adjustment creates a high-dimensional state and action space, making traditional optimization methods inadequate. To address this, we utilize the Lee-Carter model to analyze Australian demographic data, predict mortality risk, simulate surrender risk based on market changes, and estimate the fair pricing of GMDBs in the portfolio. Subsequently, we introduce a deep reinforcement learning algorithm within a simulated trading environment that independently models the dynamic behavior of various assets and underlying indices. The algorithm utilizes neural networks to analyze high-dimensional state variables and leverages the interactive capabilities of the agent to flexibly adapt to asset fluctuations, dynamically optimizing investment allocation. Additionally, we prove the global convergence of the algorithm under standard assumptions and validate its effectiveness in managing the complexities of high-dimensional portfolios, particularly in capturing mortality, surrender, and financial risks. Numerical experiments further demonstrate the stability and robustness of the algorithm, showcasing its advantages in complex insurance and financial scenarios.

Speaker

Huang Huifang is a Ph.D. candidate in Statistics at the School of Mathematics and Statistics, Huazhong University of Science and Technology (HUST), China. Her research specializes in stochastic optimal control, numerical methods for actuarial science, and deep reinforcement learning, with a focus on developing computational frameworks to solve complex actuarial problems. As a recipient of the prestigious China Scholarship Council (CSC) Fellowship, she pursued joint doctoral research at Macquarie University, Australia.