An analysis on operational risk in international banking: A Bayesian approach (2007–2011)

This study aims to develop a Bayesian methodology to identify, quantify and measure operational risk in several business lines of commercial banking. To do this, a Bayesian network (BN) model is designed with prior and subsequent distributions to estimate the frequency and severity. Regarding the subsequent distributions, an inference procedure for the maximum expected loss, for a period of 20 days, is carried out by using the Monte Carlo simulation method. The business lines analyzed are marketing and sales, retail banking and private banking, which all together accounted for 88.5% of the losses in 2011. Data was obtained for the period 2007–2011 from the Riskdata Operational Exchange Association (ORX), and external data was provided from qualified experts to complete the missing records or to improve its poor quality.

[1]  Jose A. Lopez.  What is operational risk , 2002 .

[2]  T. Ferguson.  A Bayesian Analysis of Some Nonparametric Problems , 1973 .

[3]  Arnold Zellner,et al.  An Introduction to Bayesian Inference in Econometrics. , 1974 .

[4]  Carol Alexander,et al.  Operational Risk Measurement: Advanced Approaches , 2002 .

[5]  Paul Embrechts,et al.  QUANTIFYING REGULATORY CAPITAL FOR OPERATIONAL RISK , 2003 .

[6]  David J. Spiegelhalter,et al.  Probabilistic Networks and Expert Systems , 1999, Information Science and Statistics.

[7]  J. Pearl.  Causality: Models, Reasoning and Inference , 2000 .

[8]  Norman Fenton,et al.  Using Bayesian Networks to Model Expected and Unexpected Operational Losses , 2005, Risk analysis : an official publication of the Society for Risk Analysis.

[9]  Philippe Artzner,et al.  Coherent Measures of Risk , 1999 .

[10]  A. Zellner.  An Introduction to Bayesian Inference in Econometrics , 1971 .

[11]  Gareth W. Peters,et al.  Fundamental Aspects of Operational Risk and Insurance Analytics: A Handbook of Operational Risk , 2015 .

[12]  Harry H. Panjer,et al.  Operational Risk : Modeling Analytics , 2006 .

[13]  Mario Markus,et al.  Multipeaked probability distributions of recurrence times. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  David J. Spiegelhalter,et al.  Local computations with probabilities on graphical structures and their application to expert systems , 1990 .

[15]  Reimer Kühn,et al.  Phase transitions in operational risk. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[16]  Marco Moscadelli,et al.  The Modelling of Operational Risk: Experience with the Analysis of the Data Collected by the Basel Committee , 2004 .

[17]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[18]  William H. Hsu,et al.  A Survey of Algorithms for Real-Time Bayesian Network Inference , 2002 .

[19]  Paul Embrechts,et al.  The Quantitative Modeling of Operational Risk: Between G-and-H and EVT , 2007, ASTIN Bulletin.

[20]  Chris Kenyon,et al.  Cause-To-Effect Operational-Risk Quantification and Management , 2006 .

[21]  F. Venegas-Martínez,et al.  Riesgos financieros y económicos , 2008 .

[22]  Peter Neu,et al.  Functional correlation approach to operational risk in banking organizations , 2002 .

[23]  F. De Carlo,et al.  A Bayesian Networks approach to Operational Risk , 2009, 0906.3968.

[24]  Lakhmi C. Jain,et al.  Introduction to Bayesian Networks , 2008 .

[25]  R. Kuehn,et al.  Adequate Capital and Stress Testing for Operational Risks , 2004 .

[26]  T. Ferguson.  Prior Distributions on Spaces of Probability Measures , 1974 .

[27]  A. Hasman,et al.  Probabilistic reasoning in intelligent systems: Networks of plausible inference , 1991 .

[28]  F. Venegas-Martínez.  Riesgos financieros y económicos, productos derivados y decisiones económicas bajo incertidumbre , 2008 .

[29]  Marcelo Cruz.  Modeling, Measuring and Hedging Operational Risk , 2002 .