Multivariate Dependence Modeling of Cyber Breach Risks with Insurance Applications

31 Pages Posted: 20 Sep 2024

See all articles by Yijia Li

Yijia Li

University of Science and Technology of China (USTC)

Maochao xu

Illinois State University

he wang

Dongbei University of Finance and Economics

Peng zhao

Jiangsu Normal University

Multiple version iconThere are 2 versions of this paper

Abstract

Cyber breaches pose a significant threat to enterprises and society at large. Analyzing data on cyber breach incidents is crucial for enhancing cyber risk management and developing effective cyber insurance policies. However, modeling cyber risk presents several challenges due to its characteristics, such as sparsity, heterogeneity, heavy tails, and dependence. This work introduces a novel multivariate dependence model that captures both temporal and cross-group dependencies to more accurately represent multivariate cyber breach risks. The proposed framework employs a semi-parametric approach to model breach sizes, while the multivariate dependence is modeled via a copula approach. Our findings, supported by both empirical and synthetic studies, demonstrate that the proposed model captures the statistical characteristics of multivariate cyber breach risks well and outperforms commonly used models in the literature in terms of predictive performance. Additionally, we show that our approach can generate more profitable insurance contracts in the context of insurance pricing .

Keywords: copula, Heterogeneity, Heavy-tail risks, Rosenblatt transform, Sparsity.

Suggested Citation

Li, Yijia and xu, Maochao and wang, he and zhao, Peng, Multivariate Dependence Modeling of Cyber Breach Risks with Insurance Applications. Available at SSRN: https://ssrn.com/abstract=4962271 or http://dx.doi.org/10.2139/ssrn.4962271

Yijia Li

University of Science and Technology of China (USTC) ( email )

No. 96 Jinzhai Road
Hefei, 230026
China

Maochao Xu

Illinois State University ( email )

Normal, IL 61790
United States

He Wang (Contact Author)

Dongbei University of Finance and Economics ( email )

Peng Zhao

Jiangsu Normal University ( email )

101 Shanghai Rd
Tongshan
Xuzhou
China

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
25
Abstract Views
105
PlumX Metrics