Events

Hybrid Data Mining Framework for Variable Annuity Portfolio

Abstract:
A variable annuity is a modern life insurance product that offers its policyholders participation in investment with various guarantees. To address the computational challenge of valuing large portfolios of variable annuity contracts, several data mining frameworks based on statistical learning have been proposed in the past decade. Existing methods utilize regression modeling to predict the market value of most contracts. Despite the efficiency of those methods, a regression model fitted to a small amount of data produces substantial prediction errors, and thus, it is challenging to rely on existing frameworks when highly accurate valuation results are desired or required. In this paper, we propose a novel hybrid framework that effectively chooses and assesses easy-to-predict contracts using the random forest model while leaving hard-to-predict contracts for the Monte Carlo simulation. The effectiveness of the hybrid approach is illustrated with an experimental study.

Speaker:
Dr. Hyukjun (Jay) Gweon is an assistant professor in the department of statistical and actuarial sciences at Western University, Canada. He earned his Ph.D. in Statistics from the University of Waterloo. His research focuses on data-driven predictive modeling and its applications in actuarial science, with the goal of enhancing the use of data resources. His interests also extend to model uncertainty assessment and automated coding techniques for text and survey data.

Registration Options:

I am a member of an IAA Section (AFIR-ERM; ASTIN; IAAHS; IAALS; IACA OR PBSS): This category applies to individuals whose membership with an IAA Section expires December 31, 2025 or later.
I am subscribing to the AFIR-ERM Section today: By choosing this option, you will receive AFIR-ERM member benefits until December 31, 2025.

Important Notes:

You must be signed into your IAA account to register.
To complete your registration, click the "Proceed to check-out" button and lastly click on the "Submit" button to complete your order.
Once successfully registered, you will receive an automated response with your individual Zoom link to add to your personal calendar.
In addition to the Zoom link, you will also receive a confirmation email from the IAA Secretariat.
If you need assistance with your registration; please contact Teboho Mabeba, Section Coordinator

Sign in
Create an account

When

1/21/2025