A hybrid deep learning method for optimal insurance strategies: Algorithms and convergence analysis

被引:12
作者
Jin, Zhuo [1 ]
Yang, Hailiang [2 ]
Yin, G. [3 ]
机构
[1] Univ Melbourne, Ctr Actuarial Studies, Dept Econ, Melbourne, Vic 3010, Australia
[2] Univ Hong Kong, Dept Stat & Actuarial Sci, Hong Kong, Peoples R China
[3] Univ Connecticut, Dept Math, Storrs, CT 06269 USA
基金
美国国家科学基金会;
关键词
Neural network; Deep learning; Markov chain approximation; Stochastic approximation; Investment; Reinsurance; Dividend management; Convergence; JUMP DIFFUSION-MODELS; OPTIMAL INVESTMENT; OPTIMIZATION; POLICIES;
D O I
10.1016/j.insmatheco.2020.11.012
中图分类号
F [经济];
学科分类号
02 ;
摘要
This paper develops a hybrid deep learning approach to find optimal reinsurance, investment, and dividend strategies for an insurance company in a complex stochastic system. A jump-diffusion regime-switching model with infinite horizon subject to ruin is formulated for the surplus process. A Markov chain approximation and stochastic approximation-based iterative deep learning algorithm is developed to study this type of infinite-horizon optimal control problems. Approximations of the optimal controls are obtained by using deep neural networks. The framework of Markov chain approximation plays a key role in building iterative algorithms and finding initial values. Stochastic approximation is used to search for the optimal parameters of neural networks in a bounded region determined by the Markov chain approximation method. The convergence of the algorithm is proved and the rate of convergence is provided. (C) 2020 Elsevier B.V. All rights reserved.
引用
收藏
页码:262 / 275
页数:14
相关论文
共 31 条
[1]  
Albrecher H., 2017, Reinsurance: Actuarial and statistical aspects
[2]  
ALEANDRI M., 2018, WORKING PAPER
[3]  
[Anonymous], 2018, ARXIV181204300
[4]  
[Anonymous], 2003, Stochastic Modelling and Applied Probability
[5]  
ARROW KJ, 1963, AM ECON REV, V53, P941
[6]  
Bachouch A., 2018, ARXIV181205916
[7]  
Borch K., 1960, ASTIN Bulletin, V1, P170, DOI [10.1017/S0515036100009557, DOI 10.1017/S0515036100009557]
[9]   OPTIMAL INSURANCE STRATEGIES: A HYBRID DEEP LEARNING MARKOV CHAIN APPROXIMATION APPROACH [J].
Cheng, Xiang ;
Jin, Zhuo ;
Yang, Hailiang .
ASTIN BULLETIN, 2020, 50 (02) :449-477
[10]  
De Finetti Bruno, 1957, Transactions of the XVth International Congress of Actuaries, V2, P433