Statistical Machine Learning Analysis of Cyber Risk Data: Event Case Studies

Abstract

This work explores the common attributes of different types of cyber risk with a view to better understanding the key attributes that contribute to each type of cyber risk category. In doing so we will explore event studies on a range of different market sectors, different countries, different demographics over time and categories of cyber risk event type.

To perform this study we will explore a modern machine learning based clustering method to explore the attributes of cyber risk and how they statistically can be categorized. We will then explore the properties of this statistics classification and interpret its implications for the current taxonomies being developed for this area of risk management.

In the process we will interpret and analyze the implications our analysis has on both operational risk modelling of cyber risk data, as well as the implications the findings have for cyber risk insurance products.

Keywords: Cyber Risk, Cyber Crime, Operational Risk, Cyber Insurance, Kernel K-Means, Clustering, Cyber Empirical Studies