Journal of Operational Risk

Risk.net

A note on the standard measurement approach versus the loss distribution approach–advanced measurement approach: the dawning of a new regulation

Andrés Mora-Valencia

  • The BCBS proposal, SMA, is backward-looking measure and risk insensitive.
  • Median shortfall could achieve the objective of non-significant increase in capital. 
  • Bayesian model averaging is proposed to mitigate model uncertainty problem in OpRisk.

A recent Basel Committee on Banking Supervision publication suggesting a switch from the advanced measurement approach (AMA) to the standard measurement approach (SMA) has generated debate in the financial industry and among academics regarding the new rules. This note presents a nonexhaustive review of the literature on operational risk quantification under a combination of the loss distribution approach model – the most commonly used of the AMA models – and extreme value theory. The literature review points out that Bayesian inference has provided solutions to different problems when modeling operational data. The main comments prepared by the financial industry in response to the new proposal and two recently published papers that analyze the impact of SMA are also summarized. Finally, the discussion section proposes an alternative solution – a single-loss approximation model (taking into account several severity and frequency distributions) with an appropriate risk
measure under a Bayesian model averaging setting – as an intermediate solution to estimate operational risk capital. Its application will be the focus of future research.

Sorry, our subscription options are not loading right now

Please try again later. Get in touch with our customer services team if this issue persists.

New to Risk.net? View our subscription options

You need to sign in to use this feature. If you don’t have a Risk.net account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here