Efficient Risk Models: Application of DEA Approach

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27510%2F14%3A86090952" target="_blank" >RIV/61989100:27510/14:86090952 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Efficient Risk Models: Application of DEA Approach
Original language description
Risk estimation is an important activity of any financial institution. Necessary part of risk estimation is financial time series modelling, which is challenging task due to specific features of financial time series. Suitability of any risk models can be assessed by the so-called backtesting procedure. Applying this procedure we obtain the number of violations, i.e. the cases in which observed loss is higher than estimated risk (mostly measured as VaR). For accurate model the quantity of VaR violations in the long term should converge to the quantity expected. It can be computed as the risk level multiplied by the number of backtesting days. The lower the difference between observed and expected quantities, the more accurate the model is. However, we can assume various risk levels. Then, the selection of the best model will become difficult, or even impossible. However, we can construct the set of efficient models, for example, using a data envelope analysis (DEA) approach.
Czech name
—
Czech description
—

Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
CIE 2014 - 44th International Conference on Computers and Industrial Engineering and IMSS 2014 - 9th International Symposium on Intelligent Manufacturing and Service Systems...
ISBN
978-1-63439-679-0
ISSN
—
e-ISSN
neuvedeno
Number of pages
12
Pages from-to
976-987
Publisher name
Curran Associates
Place of publication
New York
Event location
Istanbul
Event date
Oct 14, 2014
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)