Statistical machine learning analysis of cyber risk data: event case studies

Gareth W. Peters, Pavel V. Shevchenko, Ruben D. Cohen, Diane R. Maurice

Research output: Chapter in Book/Report/Conference proceedingChapterResearchpeer-review

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
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 explore a modern machine learning
clustering method to investigate the attributes of cyber risk
and how they can be categorised via a statistical method. We then
explore the properties of this statistical classification and interpret
its implications for the current taxonomies being developed for
cyber risk in areas of risk management. In the process we will interpret and analyse 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. On a broader level, this analysis informs risk
behaviour of both traditional and emerging financial institutions
such as financial technology (fintech).
LanguageEnglish
Title of host publicationFintech
Subtitle of host publicationGrowth and Deregulation
EditorsDiane Maurice, David Fairman, Jack Freund
Place of PublicationUnited Kingdom
PublisherRisk Books
Chapter3
Pages75-99
Number of pages25
ISBN (Electronic)9781782723981
ISBN (Print)9781782723875
Publication statusPublished - 19 Feb 2018

Fingerprint

Machine learning
Insurance risk
Event risk
Taxonomy
Statistical methods
Risk management
Demographics
Operational risk
Event study
Modeling

Keywords

  • Cyber Risk
  • Cyber Crime
  • Operational Risk
  • Cyber Insurance
  • Kernel K-Means
  • Clustering
  • Cyber Empirical Studies

Cite this

Peters, G. W., Shevchenko, P. V., Cohen, R. D., & Maurice, D. R. (2018). Statistical machine learning analysis of cyber risk data: event case studies. In D. Maurice, D. Fairman, & J. Freund (Eds.), Fintech: Growth and Deregulation (pp. 75-99). United Kingdom: Risk Books.
Peters, Gareth W. ; Shevchenko, Pavel V. ; Cohen, Ruben D. ; Maurice, Diane R. / Statistical machine learning analysis of cyber risk data : event case studies. Fintech: Growth and Deregulation. editor / Diane Maurice ; David Fairman ; Jack Freund. United Kingdom : Risk Books, 2018. pp. 75-99
@inbook{1c979c485daf400fb7ec1f9b4e84691f,
title = "Statistical machine learning analysis of cyber risk data: event case studies",
abstract = "This work explores the common attributes of different types ofcyber risk with a view to better understanding the key attributesthat contribute to each type of cyber risk category. In doing so weexplore event studies on a range of different market sectors,different countries, different demographics over time and categoriesof cyber risk event type.To perform this study we explore a modern machine learningclustering method to investigate the attributes of cyber riskand how they can be categorised via a statistical method. We thenexplore the properties of this statistical classification and interpretits implications for the current taxonomies being developed forcyber risk in areas of risk management. In the process we will interpret and analyse 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. On a broader level, this analysis informs riskbehaviour of both traditional and emerging financial institutionssuch as financial technology (fintech).",
keywords = "Cyber Risk, Cyber Crime, Operational Risk, Cyber Insurance, Kernel K-Means, Clustering, Cyber Empirical Studies",
author = "Peters, {Gareth W.} and Shevchenko, {Pavel V.} and Cohen, {Ruben D.} and Maurice, {Diane R.}",
year = "2018",
month = "2",
day = "19",
language = "English",
isbn = "9781782723875",
pages = "75--99",
editor = "Diane Maurice and David Fairman and Jack Freund",
booktitle = "Fintech",
publisher = "Risk Books",

}

Peters, GW, Shevchenko, PV, Cohen, RD & Maurice, DR 2018, Statistical machine learning analysis of cyber risk data: event case studies. in D Maurice, D Fairman & J Freund (eds), Fintech: Growth and Deregulation. Risk Books, United Kingdom, pp. 75-99.

Statistical machine learning analysis of cyber risk data : event case studies. / Peters, Gareth W.; Shevchenko, Pavel V.; Cohen, Ruben D.; Maurice, Diane R.

Fintech: Growth and Deregulation. ed. / Diane Maurice; David Fairman; Jack Freund. United Kingdom : Risk Books, 2018. p. 75-99.

Research output: Chapter in Book/Report/Conference proceedingChapterResearchpeer-review

TY - CHAP

T1 - Statistical machine learning analysis of cyber risk data

T2 - event case studies

AU - Peters, Gareth W.

AU - Shevchenko, Pavel V.

AU - Cohen, Ruben D.

AU - Maurice, Diane R.

PY - 2018/2/19

Y1 - 2018/2/19

N2 - This work explores the common attributes of different types ofcyber risk with a view to better understanding the key attributesthat contribute to each type of cyber risk category. In doing so weexplore event studies on a range of different market sectors,different countries, different demographics over time and categoriesof cyber risk event type.To perform this study we explore a modern machine learningclustering method to investigate the attributes of cyber riskand how they can be categorised via a statistical method. We thenexplore the properties of this statistical classification and interpretits implications for the current taxonomies being developed forcyber risk in areas of risk management. In the process we will interpret and analyse 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. On a broader level, this analysis informs riskbehaviour of both traditional and emerging financial institutionssuch as financial technology (fintech).

AB - This work explores the common attributes of different types ofcyber risk with a view to better understanding the key attributesthat contribute to each type of cyber risk category. In doing so weexplore event studies on a range of different market sectors,different countries, different demographics over time and categoriesof cyber risk event type.To perform this study we explore a modern machine learningclustering method to investigate the attributes of cyber riskand how they can be categorised via a statistical method. We thenexplore the properties of this statistical classification and interpretits implications for the current taxonomies being developed forcyber risk in areas of risk management. In the process we will interpret and analyse 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. On a broader level, this analysis informs riskbehaviour of both traditional and emerging financial institutionssuch as financial technology (fintech).

KW - Cyber Risk

KW - Cyber Crime

KW - Operational Risk

KW - Cyber Insurance

KW - Kernel K-Means

KW - Clustering

KW - Cyber Empirical Studies

UR - https://ssrn.com/abstract=3073704

M3 - Chapter

SN - 9781782723875

SP - 75

EP - 99

BT - Fintech

A2 - Maurice, Diane

A2 - Fairman, David

A2 - Freund, Jack

PB - Risk Books

CY - United Kingdom

ER -

Peters GW, Shevchenko PV, Cohen RD, Maurice DR. Statistical machine learning analysis of cyber risk data: event case studies. In Maurice D, Fairman D, Freund J, editors, Fintech: Growth and Deregulation. United Kingdom: Risk Books. 2018. p. 75-99