Research and Case Study on Insurance Underwriting Decision Making Based on LSTM, SVM and Random Forest Modeling
DOI:
https://doi.org/10.62051/jp687g58Keywords:
Insurance Underwriting Decisions; Binary Classification Model.Abstract
In recent years, the world has suffered from a variety of extreme weather events, which are gradually becoming a crisis for insurance companies and homeowners. To address the challenges of insurance companies in their underwriting decisions for a specific region, this paper proposes a binary classification model for determining whether they should be underwritten, with an output of 1 (underwritten) or 0 (not underwritten). Firstly, extreme weather events are identified by screening the number of casualties, property and crop losses and quantifying the impact of these events. Then, a system of metrics was developed, including the use of LSTM models to predict risk indicators. Correlation analyses were conducted to verify the validity of the indicator system, and then the quantitative data were fed into SVM models and random forest models to solve the classification problem. Finally, recommendations for insurance companies and homeowners were made based on the results, and two regions on different continents were selected to demonstrate the effectiveness of the model.
Downloads
References
[1] Zhang Yue. Research on the size measurement of catastrophe insurance fund in China [D]. Sichuan: Southwest University of Finance and Economics, 2023.
[2] Zhang Litian, Bu Qingjie, Yang Guihua, et al. Problems of the correct use of commonly used mathematical and statistical methods in academic papers in the field of environmental sciences [J]. Journal of Environmental Science, 2007 (1): 171 - 173.
[3] A SVM based ship collision risk assessment algorithm[J]. Ocean engineering,2020, 202 (Apr.15): 107062. 1 - 107062. 11.
[4] Yao Tianlei, Chen Xiliang, Yu Peiyi. Review of generative reinforcement learning studies based on sequence modeling [J/OL]. computer science.
[5] L. Zhou and Y. Cui, Parameter Optimization and Its Application of Support Vector Machines Based on Improved Particle Swarm Optimization Algorithm.2022 4th International Conference on Intelligent Information Processing (IIP), Guangzhou, China, 2022, pp. 213 - 216.
[6] Zou Xiang, Liu Ton, Huang Pu, et al. An intelligent prediction method of natural gas consumption based on LSTM [J]. Automation Expo, 2023, 40 (6): 60 - 64.
[7] Chen Yamin, Wang Ke, Wang Zhan, Wang Huiqin, Li Yuan, Zhen Gang. Pigment classification method for mural multispectral images based on multiscale superpixel segmentation [J/OL]. Progress in laser light and optoelectronics.
[8] R. Zhang, W. Wang. Facilitating the applications of support vector machine by using a new kernel [J]. Expert Systems with Applications, 2011 38 (11): 14225 - 14230.
[9] G. F. Smits, E. M. Jor dan. Improved SVM regression using mixtures of kernels [C]. International Joint Conference on Neural Networks. IEEE Xplore, 2002.
[10] Huang Mingfeng, Du Hai, Wang Qing et al. Typhoon extreme wind speed prediction for cities and offshore waters along the southeast coast of China [J]. Journal of Building Structures, 2024, 45 (05): 104 - 114.
Downloads
Published
Conference Proceedings Volume
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.