A review of the state of the art in quantifying operational risk

Sonia Benito; Carmen López Martín

Save this article

Need to know

The empirical literature shows that the negative binomial distribution and in general the non-homogeneous process overcomes Poisson and binomial distributions in modeling frequency data.
In modeling severity data, the empirical literature shows that heavy-tailed distributions fit better than light-tailed distributions.
In this paper, we review the truncated method to fit properly operational data, which are naïve, truncated and the shifted approach.
The scarcity of operational data obligates the firms to integrate external with their internal data base.

Abstract

In this paper, we provide a comprehensive review of the different approaches developed to model operational risk, specifically focusing on the actuarial approach. We highlight their relative strengths and weaknesses. In the case of the actuarial approach – that most commonly used by financial institutions – we review the challenges faced (scarcity of data, truncated data, and modeling dependence in both frequency and severity) and offer proposals to overcome them. Our paper’s objective is to provide financial risk researchers with all of the models and proposed developments for operational risk estimation.

As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (point 2.4), printing is limited to a single copy.

If you would like to purchase additional rights please email info@risk.net

You may share this content using our article tools. As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (clause 2.4), an Authorised User may only make one copy of the materials for their own personal use. You must also comply with the restrictions in clause 2.5.

If you would like to purchase additional rights please email info@risk.net