Reinforcement Learning-Based Dynamic Pricing Strategy for Life Insurance in a Low-Interest Rate Environment

DOI

10.2991/978-94-6239-672-2_50How to use a DOI?

Keywords

Low-Interest Rate Environment; Dynamic Life Insurance Pricing; MDP; DQN; Interest Margin Loss

Abstract

Under the low-interest rate environment, the life insurance industry’s interest margin loss risk accumulates continuously, and traditional static and heuristic threshold pricing struggle to balance risk control, customer retention and enterprise benefits. Taking whole life insurance as the research object, this paper constructs an MDP-DQN dynamic pricing model by depicting the pricing sequential decision-making via Markov Decision Process (MDP) and solving the high-dimensional state problem with Deep Q-Network (DQN). Based on 2013–2025 10-year Treasury bond yields, a simulated policy pool is built for three pricing strategies comparison. The results show that compared with the traditional static pricing strategy, the model reduces interest margin loss by 64.3% and increases new business value by 29.6%; compared with the heuristic threshold pricing strategy, it cuts loss by 54.5% and boosts value by 65.3%, with customer churn rate stabilized within 5%, providing an effective technical solution for the industry to cope with low-interest rate risks.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Zi-Jia Yi
PY  - 2026
DA  - 2026/05/12
TI  - Reinforcement Learning-Based Dynamic Pricing Strategy for Life Insurance in a Low-Interest Rate Environment
BT  - Proceedings of the 2026 3rd International Conference on Applied Economics, Management Science and Social Development (AEMSS 2026)
PB  - Atlantis Press
SP  - 524
EP  - 534
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6239-672-2_50
DO  - 10.2991/978-94-6239-672-2_50
ID  - Yi2026
ER  -