File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

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

TitleA hybrid deep learning method for optimal insurance strategies: Algorithms and convergence analysis
Authors
KeywordsNeural network
Deep learning
Markov chain approximation
Stochastic approximation
Investment
Reinsurance
Dividend management
Convergence
Issue Date2021
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/ime
Citation
Insurance: Mathematics and Economics, 2021, v. 96, p. 262-275 How to Cite?
AbstractThis 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.
Persistent Identifierhttp://hdl.handle.net/10722/304754
ISSN
2023 Impact Factor: 1.9
2023 SCImago Journal Rankings: 1.113
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorJin, Z-
dc.contributor.authorYang, H-
dc.contributor.authorYin, G-
dc.date.accessioned2021-10-05T02:34:42Z-
dc.date.available2021-10-05T02:34:42Z-
dc.date.issued2021-
dc.identifier.citationInsurance: Mathematics and Economics, 2021, v. 96, p. 262-275-
dc.identifier.issn0167-6687-
dc.identifier.urihttp://hdl.handle.net/10722/304754-
dc.description.abstractThis 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.-
dc.languageeng-
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/ime-
dc.relation.ispartofInsurance: Mathematics and Economics-
dc.subjectNeural network-
dc.subjectDeep learning-
dc.subjectMarkov chain approximation-
dc.subjectStochastic approximation-
dc.subjectInvestment-
dc.subjectReinsurance-
dc.subjectDividend management-
dc.subjectConvergence-
dc.titleA hybrid deep learning method for optimal insurance strategies: Algorithms and convergence analysis-
dc.typeArticle-
dc.identifier.emailYang, H: hlyang@hku.hk-
dc.identifier.emailYin, G: gyin@hku.hk-
dc.identifier.authorityYang, H=rp00826-
dc.identifier.authorityYin, G=rp00831-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.insmatheco.2020.11.012-
dc.identifier.scopuseid_2-s2.0-85098599122-
dc.identifier.hkuros326290-
dc.identifier.volume96-
dc.identifier.spage262-
dc.identifier.epage275-
dc.identifier.isiWOS:000608020200019-
dc.publisher.placeNetherlands-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats