Department of

# Mathematics

Seminar Calendar
for events the day of Monday, April 19, 2021.

.
events for the
events containing

More information on this calendar program is available.
Questions regarding events or the calendar should be directed to Tori Corkery.
      March 2021             April 2021              May 2021
Su Mo Tu We Th Fr Sa   Su Mo Tu We Th Fr Sa   Su Mo Tu We Th Fr Sa
1  2  3  4  5  6                1  2  3                      1
7  8  9 10 11 12 13    4  5  6  7  8  9 10    2  3  4  5  6  7  8
14 15 16 17 18 19 20   11 12 13 14 15 16 17    9 10 11 12 13 14 15
21 22 23 24 25 26 27   18 19 20 21 22 23 24   16 17 18 19 20 21 22
28 29 30 31            25 26 27 28 29 30      23 24 25 26 27 28 29
30 31


Monday, April 19, 2021

1:00 pm in via Zoom,Monday, April 19, 2021

#### Metamodeling for variable annuity valuation: What works and what does not

###### Xiaochen Jing   [email] (University of Wisconsin, Madison)

Abstract: Variable Annuities have become popular retirement products with various options of guarantees, but their complex design also makes liability management a difficult task for insurers. There have been several dozen papers published in the past years on exploring the use of statistical learning and metamodeling approaches for Variable Annuity valuation and risk management in the actuarial science and quantitative finance literatures. However, they all focus on specific techniques in the context of synthetic data. In this paper, I investigate the effectiveness of metamodeling approaches with different experimental designs and metamodels with real-world Variable Annuity contracts. In particular, I use textual analysis to extract and formulate value-related features and develop a flexible and comprehensive simulation-based scheme for Variable Annuity valuation. I find that (1) real-world variable annuity contracts are very complex and the intricate relations between their valuation and features are difficult to obtain. And (2) the overall performance of a metamodeling method depends on the employed machine learning methods as well as the sample size---though not substantially on the sampling methods. Both improve performance at the cost of longer runtime.