Heterogeneity in cyber loss severity and its impact on cyber risk measurement
Open Access
- 6 June 2022
- journal article
- research article
- Published by Springer Nature in Risk Management
- Vol. 24 (4) , 273-297
Abstract
We use the world’s largest publicly available dataset of operational risk to model cyber losses and show that the Tweedie model best fits the cyber loss severity in the financial industry. Three key determinants of loss severity are firm size, contagion risk and legal liability. We also measure the size of risk based on the estimation results and show a large degree of heterogeneity across financial firms. The results are particularly relevant with respect to the recent discussion on simplifying operational risk capital requirements and reiterate the importance of considering individual firm characteristics when modelling operational losses.Keywords
Funding Information
- University of St.Gallen
This publication has 35 references indexed in Scilit:
- Expected shortfall estimation for apparently infinite-mean models of operational riskQuantitative Finance, 2016
- Multivariate Frequency-Severity Regression Models in InsuranceRisks, 2016
- Generalised linear models for aggregate claims: to Tweedie or not?European Actuarial Journal, 2015
- An Extreme Value Approach for Modeling Operational Risk Losses Depending on CovariatesJournal of Risk and Insurance, 2015
- Insurability of Cyber Risk: An Empirical AnalysisThe Geneva Papers on Risk and Insurance - Issues and Practice, 2014
- Insurance ratemaking using a copula-based multivariate Tweedie modelScandinavian Actuarial Journal, 2014
- A scaling model for severity of operational losses using generalized additive models for location scale and shape (GAMLSS)Annals of Actuarial Science, 2012
- Implementing loss distribution approach for operational riskApplied Stochastic Models in Business and Industry, 2010
- Capital and Risk: New Evidence on Implications of Large Operational LossesJournal of Money, Credit and Banking, 2006
- Fitting Tweedie's compound poisson model to insurance claims dataScandinavian Actuarial Journal, 1994