Managing Weather Risk with a Neural Network-Based Index Insurance

Speaker：Zhu Wenjun（Assistant professor， Nanyang University of Technology Nanyang Business School）

Host：Kang Junqing, Assistant Professor, Lingnan College

Time and Date：14:30-16:30, Jun. 10, 2022

Venue:  Wang Daohan Conference Room，Lingnan Hall

Language: English +Chinese

Meeting Link: Tencent meeting number: 514-565-350

Abstract:

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.

 Profile of the speaker:

Professor Zhu Wenjun is an assistant professor at the Department of Finance Department of Nanyang University of Technology Nanyang University of Technology. Zhu Wenjun graduated from Waterloo Statistics Actuary Department. She is the North American Actuary Association's Actuary (FSA), a registered enterprise risk analyst (CERA). The research direction is systemic risks, machine learning, weather risk management and agricultural insurance in financial insurance. She published many articles in international journals such as Jri, IME, Naaj, JBF, Astin Bulletin.