Cyber-Risk Forecasting using Machine Learning Models and Generalized Extreme Value Distributions

Jules Sadefo Kamdem; Danielle Selambi

Back

Cyber-Risk Forecasting using Machine Learning Models and Generalized Extreme Value Distributions

Working paper

Open access

Cyber-Risk Forecasting using Machine Learning Models and Generalized Extreme Value Distributions

Jules Sadefo Kamdem and Danielle Selambi

Abstract

Cyber insurance

Cyber risk

Machine Learning

Regression Trees

Random Forest

Generalized Extreme Value

In this paper, we estimate the cost of a data breach using the number of compromisedrecords. The number of such records is predicted by means of a machine learning model,particularly the Random Forest. We further analyse the fat tail phenomena which capturethe underlying dynamics in the number of affected records. The objective is to calculatethe maximum loss in order to answer the question of the insurability of cyber risk. Ourresults show that the total number of affected records follow a Frechet distribution, andwe then estimate the Generalized Extreme Value (GEV) parameters to calculate the valueat risk (VaR). This analysis is critical because it gives an idea of the maximum loss thatcan be generated by an enterprise data breach. These results are usable in anticipatingthe premiums for cyber risk coverage in the insurance markets.

Files and links (1)

url

Find in HALView

Metrics

1 Record Views

Details

Title: Cyber-Risk Forecasting using Machine Learning Models and Generalized Extreme Value Distributions
Creators - without role: Jules Sadefo Kamdem - Université de Montpellier, Montpellier Recherche en Economie - MRE
Danielle Selambi - African Institute for Mathematical Sciences (AIMS-Cameroon)
Identifiers: 9946378609311
Academic Unit: Montpellier Recherche en Economie - MRE
Language: English
Resource Type: Working paper
Local Fields: hal-03814979