Hostname: page-component-cd9895bd7-8ctnn Total loading time: 0 Render date: 2024-12-13T09:20:21.006Z Has data issue: false hasContentIssue false

Conditional mean risk sharing in the individual model with graphical dependencies

Published online by Cambridge University Press:  17 June 2021

Michel Denuit
Affiliation:
Institute of Statistics, Biostatistics and Actuarial Science – ISBA, Louvain Institute of Data Analysis and Modeling – LIDAM, UCLouvain, Louvain-la-Neuve1348, Belgium
Christian Y. Robert*
Affiliation:
Laboratory in Finance and Insurance – LFA, CREST – Center for Research in Economics and Statistics, ENSAE Paris, Palaiseau91120, France
*
*Corresponding author. E-mail: chrobert@ensae.fr

Abstract

Conditional mean risk sharing appears to be effective to distribute total losses amongst participants within an insurance pool. This paper develops analytical results for this allocation rule in the individual risk model with dependence induced by the respective position within a graph. Precisely, losses are modelled by zero-augmented random variables whose joint occurrence distribution and individual claim amount distributions are based on network structures and can be characterised by graphical models. The Ising model is adopted for occurrences and loss amounts obey decomposable graphical models that are specific to each participant. Two graphical structures are thus used: the first one to describe the contagion amongst member units within the insurance pool and the second one to model the spread of losses inside each participating unit. The proposed individual risk model is typically useful for modelling operational risks, catastrophic risks or cybersecurity risks.

Type
Original Research Paper
Copyright
© The Author(s), 2021. Published by Cambridge University Press on behalf of Institute and Faculty of Actuaries

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Arratia, R., Goldstein, L. & Kochman, F. (2019). Size bias for one and all. Probability Surveys, 16, 161.CrossRefGoogle Scholar
Bartlett, P. (2003). Undirected Graphical Models: Chordal Graphs, Decomposable Graphs, Junction Trees, and Factorizations. Lecture Notes available online at the address http://www. stat. berkeley. edu/bartlett/courses/241A-spring2007/graphnotes.pdfGoogle Scholar
Chen, H., Cummins, J.D., Sun, T. & Weiss, M.A. (2020). The reinsurance network among US property casualty insurers: Microstructure, insolvency risk, and contagion. Journal of Risk and Insurance, 87, 253284.CrossRefGoogle Scholar
Dai, B., Ding, S. & Wahba, G. (2013). Multivariate Bernoulli distribution. Bernoulli, 19, 14651483.CrossRefGoogle Scholar
Denuit, M. (2019). Size-biased transform and conditional mean risk sharing, with application to P2P insurance and tontines. ASTIN Bulletin, 49, 591617.CrossRefGoogle Scholar
Denuit, M. (2020). Investing in your own and peers’ risks: The simple analytics of P2P insurance. European Actuarial Journal, 10, 335359.CrossRefGoogle Scholar
Denuit, M. & Dhaene, J. (2012). Convex order and comonotonic conditional mean risk sharing. Insurance: Mathematics and Economics, 51, 265270.Google Scholar
Denuit, M. & Robert, C.Y. (2020a). Large-loss behavior of conditional mean risk sharing. ASTIN Bulletin, 50, 10931122.CrossRefGoogle Scholar
Denuit, M. & Robert, C.Y. (2020b). Conditional tail expectation decomposition and conditional mean risk sharing for dependent and conditionally independent risks. Available online at the address https://dial.uclouvain.be/ CrossRefGoogle Scholar
Denuit, M. & Robert, C.Y. (2021). From risk sharing to pure premium for a large number of heterogeneous losses. Insurance: Mathematics and Economics, 96, 116126.Google Scholar
Jain, K. & Nanda, A.K. (1995). On multivariate weighted distributions. Communications in Statistics-Theory and Methods, 24, 25172539.CrossRefGoogle Scholar
Joe, H. (1997). Multivariate Models and Multivariate Dependence Concepts. CRC Press.Google Scholar
Hu, T., Xie, C. & Ruan, L. (2005). Dependence structures of multivariate Bernoulli random vectors. Journal of Multivariate Analysis, 94(1), 172195.CrossRefGoogle Scholar
Kizildemir, B. & Privault, N. (2018). Supermodular ordering of Poisson and binomial random vectors by tree-based correlations. Probability and Mathematical Statistics, 38(2), 85405.Google Scholar
Lauritzen, S. (1996). Graphical Models. Oxford University Press.Google Scholar
Lin, P., Neil, M. & Fenton, N. (2014). Risk aggregation in the presence of discrete causally connected random variables. Annals of Actuarial Science, 8, 298319.CrossRefGoogle Scholar
Navarro, J., Ruiz, J.M. & Del Aguila, Y. (2006). Multivariate weighted distributions: A review and some extensions. Statistics, 40, 5164.CrossRefGoogle Scholar
Oberoi, J.S., Pittea, A. & Tapadar, P. (2020). A graphical model approach to simulating economic variables over long horizons. Annals of Actuarial Science, 14, 2041.CrossRefGoogle Scholar
Politou, D. & Giudici, P. (2009). Modelling operational risk losses with graphical models and copula functions. Methodology and Computing in Applied Probability, 11, 6593.CrossRefGoogle Scholar
Ramsahai, R. (2020). Connecting actuarial judgment to probabilistic learning techniques with graph theory. arXiv:2007.15475v1.Google Scholar
Torrado, N. & Navarro, J. (2020). Ranking the extreme claim amounts in dependent individual risk models. Scandinavian Actuarial Journal. doi: 10.1080/03461238.2020.1830845 Google Scholar
Xie, P., Li, J., Ou, X., Liu, P. & Levy, R. (2010). Using Bayesian networks for cyber security analysis. In 2010 IEEE/IFIP International Conference on Dependable Systems & Networks (DSN).Google Scholar
Zhang, Y., Li, X. & Cheung, K.C. (2018). On heterogeneity in the individual model with both dependent claim occurences and severities. ASTIN Bulletin, 48, 817839.CrossRefGoogle Scholar
Zhang, Y., Cai, X. & Zhao, P. (2020). Ordering properties of extreme claim amounts from heterogeneous portfolios. ASTIN Bulletin, 24, 475487.Google Scholar