Download this Paper Open PDF in Browser

Extremal Events in a Bank Operational Losses

27 Pages Posted: 28 Feb 2010  

Hela Dahen

Ecole des Hautes Etudes Commerciales de Montreal (HEC)

Georges Dionne

HEC Montreal - Department of Finance

Daniel Zajdenweber

affiliation not provided to SSRN

Date Written: February 26, 2010

Abstract

Operational losses are true dangers for banks since their maximal values to signal default are difficult to predict. This risky situation is unlike default risk whose maximum values are limited by the amount of credit granted. For example, our data from a very large US bank show that this bank could suffer, on average, more than four major losses a year. This bank had seven losses exceeding hundreds of millions of dollars over its 52 documented losses of more than $1 million during the 1994-2004 period. The tail of the loss distribution (a Pareto distribution without expectation whose characteristic exponent is 0.95 ≤ ≤ 1) shows that this bank can fear extreme operational losses ranging from $1 billion to $11 billion, at probabilities situated respectively between 1% and 0.1%. The corresponding annual insurance premiums are evaluated to range between $350 M and close to $1 billion.

Keywords: Bank operational loss, value at risk, Pareto distribution, insurance premium, extremal event

JEL Classification: G21, G28

Suggested Citation

Dahen, Hela and Dionne, Georges and Zajdenweber, Daniel, Extremal Events in a Bank Operational Losses (February 26, 2010). Available at SSRN: https://ssrn.com/abstract=1560026 or http://dx.doi.org/10.2139/ssrn.1560026

Hela Dahen

Ecole des Hautes Etudes Commerciales de Montreal (HEC) ( email )

3000, Chemin de la Côte-Sainte-Catherine
Montreal, Quebec H3T 2A7
Canada

Georges Dionne (Contact Author)

HEC Montreal - Department of Finance ( email )

3000 Chemin de la Cote-Sainte-Catherine
Montreal, Quebec H3T 2A7
Canada
514-340-6596 (Phone)
514-340-5019 (Fax)

HOME PAGE: http://www.hec.ca/gestiondesrisques/

Daniel Zajdenweber

affiliation not provided to SSRN ( email )

Paper statistics

Downloads
162
Rank
155,324
Abstract Views
715