Open AccessLoss distribution approach for company operational risk analysis
Author(s) -
M. Z. Fuadi,
Rosita Kusumawati,
Syarifah Inayati,
Sahid
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1581/1/012016
Subject(s) - monte carlo method , operational risk , value at risk , fast fourier transform , log normal distribution , econometrics , bayesian probability , poisson distribution , measure (data warehouse) , statistics , risk measure , distribution (mathematics) , computer science , mathematics , reliability engineering , risk management , engineering , portfolio , economics , finance , algorithm , data mining , mathematical analysis
The measurement of potential operational losses as an assessment of capital adequacy is needed by the company. One value that can be used to measure the potential loss of a company is Value at Risk (VaR). This paper aims to measure VaR based on the loss distribution using the Bayesian method where the loss frequency is assumed to be Poisson distribution and the loss severity is assumed to be the distribution Lognormal. VaR with Monte Carlo (MC) and Fast Fourier Transformation (FFT) simulations are compute using the values of the parameter of distributions that have been obtained by using the Bayesian method. In this paper, a numerical example of VaR estimation of a bank company is demonstrated to find the estimate VaR from several sources i.e. internal fraud, external fraud, business practices, employment practices, process failure, system failure and damage to assets. The results showed that the estimate VaR value equal to $ 8.2336044 with Monte Carlo and and $8.522028 with FFT simulation at 99% confidence level. These means that the company has the opportunity to experience operational risk losses which exceeds $ 8.2336044 and $8.522028 in the coming year by 1%.