Cyber modelling masks scale of potential losses, study finds

Different statistical approaches produce big variations in future loss estimates, says Esma researcher

New analysis of cyber risk losses affecting financial firms shows that applying different modelling techniques to historical datasets can produce wildly differing estimates of loss incidence. The study has implications for banks’ own projections of their potential exposure to losses, and the adequacy of cyber insurance cover provided by underwriters.

In research to be published in the Journal of Operational Risk in June, Antoine Bouveret, a senior economist at the European Securities and