Operational Value-at-Risk
About the Lecture
The lecture Operational Value-at-Risk by Edu Pristine is from the course ARCHIV Operational Risk & Risk Management Practices. It contains the following chapters:
- Summary of Basel II approaches for operational risk capital calculation
- AMA capital requirement
- Loss data approach
- Frequency distribution
- Severity distribution
- Aggregating Operational Risk Capital (ORC)
Author of lecture Operational Value-at-Risk
Edu Pristine
Customer reviews
5,0 of 5 stars
| 5 Stars |
|
5 |
| 4 Stars |
|
0 |
| 3 Stars |
|
0 |
| 2 Stars |
|
0 |
| 1 Star |
|
0 |
Excerpts from the accompanying material
... Learning Outcome Statement - The candidate should be able to: Explain the Loss Model Approach ...
... -Internal loss data -External loss data -Scenario analysis -Business environment and internal control factors -Recognition of risk mitigation (up to 20% possible) Advanced Measurement Approach (AMA) Qualifying Criteria -No specific criteria -Compliance with the Basel Committee’s “Sound Practices for the Management and Supervision of Operational Risk” recommended -Active involvement of board of directors & senior ...
... Actuarial model -Bank collects its internal operational loss data. On basis of frequency and severity of internal (and external loss data), total loss distribution is generated. 99.9% of the resultant loss distribution is Operational ...
... severity OR like credit card frauds: High EL but low UL (i.e. low chance of extreme large losses): can be covered through provisioning -Medium ...
... time series of loss amounts (severity) and number of losses p.a. (frequency) for a given type of distribution function (e.g. Poisson/ Binomial) Combining severity and frequency distr. (math: convolution) to get a loss distribution (prob. Of aggregated loss amount p.a.) by numerical methods - Monte-Carlo-Simulation 99.9-quantile is read from the loss ...
... particular period -Usually it is assumed that frequency and severity distributions are independent. -Monte-Carlo-Simulation or Numerical methods are used to combine frequency and severity distributions to obtain total loss distribution -Basel II guidelines require capital equal to 99.9 percentile ...
... distribution -Requires two parameters N: Total number of events. For instance, for trading activity, N could be target number of ...
... may also be estimated by multiplying total number of events (N) by probability (p) of observing that loss type. i.e. ? = N × p ...
... be estimated. Choice of model should depend on -Type of data -Source of loss data: Internal, External or through risk self-assessments (RCSA) ...
... Extreme Value Theory to severity distributions: EVT consists of distribution family known as Generalized Pareto Distribution (GPD). GPD is distribution of scaled excesses over a high threshold. In GPD, severity may ...
... loss distribution. These formulae are based on what the Basel Committee has called the ‘internal measurement approach’ (IMA). The basic formula for the IMA risk capital calculation given in the proposed Basel 2 Accord is given by: -ORC = Gamma × Expected annual loss = ? × NpL, where N is a volume indicator (a proxy for the number of operational events), p ...
... aggregation is very difficult even within market and credit risks - it is a very thorny issue in operational risk! Dependencies between operational risks are common. Indeed, they occur whenever two operational risk types share a common key risk driver. For instance, ...
... the VaR metric is applied, banks will make just two simple assumptions: -Full dependency: This implies risks should simply be added to obtain the total risk; this is an approximate ...
