返回顶部
   

最新推荐

当前位置:中山大学岭南(大学)学院 >> 学术报告 >> 正文内容

(5-18PM2:30)第480期岭南学术论坛(金融学系列Seminar)

【字体: 】【打印文章

报告题目:Efficient Simulation Design for Risk Management of Large Variable Annuity Portfolios

报 告 人:Ben Feng(加拿大滑铁卢大学 助理教授)

主 持 人:曾燕(中山大学岭南学院 教授)

时      间:2018年5月18日(周五)下午14:30-16:00

地      点:岭南堂黄炳礼会议室

语      言:中文+英文

 

摘要:

Variable Annuities (VAs) have been popular insurance products in practice and have attracted significant research attention in the last few decades. From the insurer's perspective, it is essential to valuate a large portfolio of VAs for different strategic goals such as those in enterprise risk management.

For accurate valuation of individual VA contracts, Monte Carlo simulation is usually required due to the contracts’ complexities. However, the computational resources required for valuing all contracts in a large VA portfolio using standard Monte Carlo could be prohibitively expensive. In the last few years, there have been numerous research efforts which apply machine learning methods to the valuation of large portfolios of VAs. All of the proposed methods show superior computational efficiencies compared to the standard Monte Carlo experiment. However, it is unclear whether these proposals have leveraged the full power of the employed machine learning methods.

The current research aims to provide a comprehensive comparison among some of recently proposed machine learning methods for large VA portfolio valuation. In particular, we identify pitfalls in some of the methods and propose corresponding improvements. Moreover, we propose, analyze, and test a new valuation method based on our suggested improvements. We show that resulting procedure has both higher accuracy and lower computational requirement than the previously proposed methods.

 

报告人介绍:

Professor Feng’s research interests include quantitative risk management, financial engineering, Monte Carlo simulation design and analysis, and nonlinear optimization.

Professor Feng is particularly interested in the intersection of these fields such as statistical machine learning, portfolio optimization, efficient simulation algorithms for risk management, etc. As an Associate of Associate of the Society of Actuaries (ASA), Professor Feng is keen in applying advanced theoretical methodologies to tackle complex practical problems in actuarial science and quantitative finance.

Professor Feng’s current research topics include:

  • Green simulation: reusing outputs in repeated simulation experiments
  • Efficient experiment design for nested simulations
  • Risk management for variable annuities
  • Machine learning in actuarial science
  • Data-driven decision making
  • Operations research

 

 

 

 

        欢迎感兴趣的年轻老师和博士生参加!

        中山大学岭南学术论坛分经济、金融和管理三个系列,是定期邀请国内外优秀学者前来开展学术交流的平台。每系列每个月定期举办2-3次。目前已经成功举办多期,并得到了各界的高度评价。

        论坛主页:http://lingnan.sysu.edu.cn/seminar/

 

打印文章】【关闭
   © 2000-2018 中山大学 版权所有  粤ICP备05008892号 | 中山大学 | 联系我们 | 网站地图 | 人才招聘 | 图书馆