乐鱼在线登录|官网入口

乐鱼在线登录

Managing Weather Risk with a Neural Network-Based Index Insurance(基于神经网络的指数保险和气象风险管理)

时间:2022-04-12         阅读:

光华讲坛——社会名流与企业家论坛第6075

主题:Managing Weather Risk with a Neural Network-Based Index Insurance(基于神经网络的指数保险和气象风险管理)

主讲人:南洋理工大学商学院 张劲弓助理教授

主持人:乐鱼在线登录金融学院 朱霄白副教授

时间:2022年4月15日(星期五)上午10:00-11:00

举办地点:腾讯会议,会议ID:574-891-308

主办单位:金融学院 科研处

主讲人简介

Jinggong Zhang (张劲弓) is an assistant professor in Nanyang Business School at Nanyang Technological University, Singapore. He obtained his PhD in actuarial science at the University of Waterloo. He is a Fellow of the Society of Actuaries and he was a Society of Actuaries James C. Hickman Scholar 2015-2018. His research interests include actuarial science, risk management and finance.

张劲弓教授为南洋理工大学南洋商学院的助理教授。张教授毕业于滑铁卢统计精算系,研究方向为风险管理,在EJOR,IME,ASTIN Bulletin等国际期刊上发表多篇文章。

内容简介

Weather risk affects economy, agricultural production in particular. Index insurance is a promising tool to hedge against weather risk, but current piecewise-linear index insurance contracts face large basis risk and low demand. We propose embedding a neural network-based optimization scheme into an expected utility maximization problem to design the index insurance contract. Neural networks capture highly nonlinear relationship between the high-dimensional weather variables and production losses. We endogenously solve for the optimal insurance premium and demand. This approach reduces basis risk, lowers insurance premium, and increases farmers' utility. Our approach can be generalized to design other financial products.

天气风险会影响经济,尤其是对农业的生产。指数保险是一种有效的天气风险对冲工具,但目前现有的分段线性指数保险合同存在基差大、需求少的问题。我们提出将一种基于神经网络的优化方案嵌入期望效用最大化问题中来设计指数型保险。神经网络能够捕捉高维天气变量与产量损失之间的非线性关系。我们对最优保费和最优需求进行求解。该方法降低了基差风险,降低了保险费用,提高了农民的效用。我们的方法可以推广到其他金融产品的设计中。