Research on Property Insurance Profit Forecasting Model and Response Strategy under Extreme Weather
DOI:
https://doi.org/10.54097/chrj4t13Keywords:
Frequent Extreme Weather, Regional Insurance Industry Profit Prediction Model, Big Data, MATLAB.Abstract
In this paper, we propose and design an insurance profit prediction model that effectively handles complex coupled variables to address the issues related to the volatility of the property insurance industry due to the frequent occurrence of extreme weather worldwide and the strong demand of insurance companies for the prediction of insurance profits in the future. Considering the adaptability of the model as well as its relocatability, we comprehensively consider the impacts of various factors on the insurance industry, such as extreme weather, geographic location, insurance market, and national development, and use them as indicators to build an insurance profit prediction model. We quantified and averaged the multivariate influences in the insurance forecasting model and solved the complex coupling variables in the model. We conducted a sensitivity analysis of the model to determine that the model has good robustness, and used this analysis to obtain a strong correlation between the ideal profit margin of the regional insurance industry and the regional insurance profit return, i.e., the ideal insurance profit margin of the regional insurance industry is a key factor affecting the total profit. Meanwhile, the model prediction results obtained by adjusting the model parameters show that under certain conditions, the regional insurance industry can obtain lower or loss profits in the short term, but is profitable in the long term. This study provides a useful reference for the property insurance industry and helps insurers to better predict profits, formulate strategies, and provide effective safeguards for property owners to meet the challenges posed by extreme weather events.
Downloads
References
Boston Consulting Group. (2023, December 4). An Insurance Risk Framework for Climate Adaptation. Retrieved at: https://www.bcg.com/publications/2023/an-insurance-risk-framework-for climate-adaptation
Munich RE. (2022, January 10). Hurricanes, cold waves, tornadoes: Weather disasters in USA dominate natural disaster losses in 2021. Retrieved at: https://www.munichre.com/en/company/media relations/ media-information-and-corporate-news/media-information/2022/natural-disaster-losses-2021.html
Xu Zhongming. Research on the sensitivity analysis method of model interrelationship parameters and its application [D]. University of Chinese Academy of Sciences (Wuhan Institute of Physics and Mathematics, Chinese Academy of Sciences), 2021.
Tan Lezhi. Looking ahead to the development trend of insurance industry in 2024 [N]. China Bank Insurance News, 2024-01-15(004).
Fang Yunlong, Lan Hong. Research on the Impact and Response of Climate-Related Risks on the Financial Sector [J]. New Finance, 2023,(06): 60-67.
Fan Liangshu. Innovative path of urban resilience governance model in the context of frequent occurrence of extreme weather [J]. National Governance, 2024(01): 73-76.
ZHOU Jianjie, YU Rengui. Theoretical research on Newton interpolation method based on MATLAB software [J]. Henan Science and Technology, 2018, (32): 10-12.
Zhang Daijun, Wan Yuting. Application of generalised regression neural network model in profit forecasting of insurance companies[C]//Chinese Insurance and Risk Management Rae-search Centre, School of Economics and Management, Tsinghua University,Cass Business School, City University London.Proceedings of the 2015 International Annual Conference on Insurance and Risk Management in China. Tsinghua University Press,2015:15.
Hu Xiaokun. Research on Influencing Factors and Forecasting of the Development of China's Insurance Industry [D]. Chengdu Information Engineering University,2019.
Wang Zexing. Study on liquidity risk contagion of insurance companies under the impact of "green swan" event [D]. East China Normal University, 2022.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.






