.png){kind=icon}
Return
Generative adversarial network stopping for robust surrendering
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ejor.2026.07.014.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate estimation of robust surrender behavior under model ambiguity is crucial for insurance companies. Existing analytical approaches are largely restricted to the Black-Scholes framework and low-dimensional settings. In this paper, we propose a generative adversarial network (GAN)-based approach to determine robust stopping rules for lapsing insurance products, with a particular focus on variable annuities. Our method is fully data-driven and readily extends to high-dimensional problems. We demonstrate its effectiveness using both simulated data and a real-world application.
Keywords:
Machine learning
Generative adversarial network
Optimal stopping problem
Deep neural network
Robust surrendering
Journal
IF:
6
Papers:
2.2W
Citations:
6.4W
Organization
View more organizations
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSave
ShareSaveShareSaveShareSaveShareSave View more