Combining scenario and historical data in the loss distribution approach: a new procedure that incorporates measures of agreement between scenarios and historical data

A fuzzy credibility model to estimate the Operational Value at Risk using internal and external data of risk events

“…To overcome the limitation of not possessing sufficient internal data, other authors [22] proposed the use of scenarios to model extreme events, which reside in the tail of the loss distributions, so that the body and the tail of the loss distribution can be modelled separately. Moreover, models have been proposed that integrate databases by using a novel approach of multidimensional credibility, which is based on Bühlmann credibility theory [23][24][25].…”

Construction of Forward-Looking Distributions Using Limited Historical Data and Scenario Assessments

“…In the remainder of the chapter we discuss the percentile approach as we believe it is the most practical of the existing approaches available in the literature. [4] That being said, it should be noted that probability assessments by experts are notoriously difficult and unreliable as discussed in [14]. We mentioned previously that it is often an extreme quantile of the aggregate loss distribution that is of interest.…”

“…We advocate the use of the so-called 1-in-c year scenario approach as discussed in [4]. In the 1-in-c years scenario approach, the experts are asked to answer the question: 'What loss level q c is expected to be exceeded once every c years?'.…”

“…In this chapter we provide an exposition of statistical methods that may be used to estimate VaR using historical data in combination with quantile assessments by experts. The proposed approach has been discussed and studied elsewhere (see [4]), but specifically in the context of operational risk and economic capital estimation. In this chapter we concentrate on the estimation of the VaR of the aggregate loss or claims distribution and strive to make the approach more accessible to a wider audience.…”

Good practice guide to setting inputs for operational risk models

“…Paper: "Combining scenario and historical data in the loss distribution approach: a new procedure that incorporates measures of agreement between scenarios and historical data" Authors: de Jongh, P., de Wet, T., Raubenheimer, H. & Venter, J. Source: Journal of Operational Risk, 2015, 10 (1) (de Jongh et al, 2015) Many banks use the loss distribution approach in their advanced measurement models to estimate regulatory or economic capital. This boils down to estimating the 99.9% value at risk of the aggregate loss distribution and is difficult to do accurately Also, it is well known that the accuracy with which the tail of the loss severity distribution is estimated is the most important driver in determining a reasonable estimate of regulatory capital To this end, banks use internal data and external data (jointly referred to as historical data) as well as scenario assessments in their endeavour to improve the accuracy with which they estimate the severity distribution This paper proposed a simple new method whereby the severity distribution may be estimated using both historical data and experts' scenario assessments Good practice guide to setting inputs for operational risk models Table A1.…”