PROBABILISTIC MODELLING OF OPERATIONAL RISKS

Authors

DOI:

https://doi.org/10.20535/kpisn.2021.3.251681

Keywords:

operational risks, probabilistic modelling, Bayesian methodology, expert estimates, actuarial processes

Abstract

Background. Operational risks are inherent to all types of human activity, including industrial production, transport, financial services, etc. Risks of this kind are characterized by many uncertainties, incompleteness and low data quality, that complicate prediction and assessment. To perform modelling of the process associated with operational risk it is necessary to carry out a proper data processing as well as identification, taking into consideration possible uncertainties. The probabilistic approach to modelling is very helpful in solving the problems.

Objective. The purpose of the paper is to make brief overview of probabilistic data analysis methods designed to build mathematical models of operational risks. To develop a new probabilistic model in the form of a Bayesian network to describe formally the operational risk of fraud associated with actuarial processes.

Methods. The basic methodology used for data and expert estimates processing are Bayesian data analysis techniques that help to construct probabilistic models in the form of Bayesian networks.

Results. The proposed modelling method was applied to constructing model of operational risk, more specifically risk of fraud in actuarial sphere. To construct the model the problem was analysed, a set of variables was selected, and prior estimates for conditional probabilities were estimated. The final model was constructed using the modelling system GeNIe. The model functioning was demonstrated using illustrative example.

Conclusions. It was shown that modelling, estimating and forecasting financial and other types of risks is important practical problem that can be solved using probabilistic approach, namely Bayesian methodology that helps to identify and take into consideration possible uncertainties of data and expert estimates. The operational risk model constructed using the methodology illustrates the possibilities of app.

References

Basel Committee on Banking Supervision. International Convergence of Capital Measurement and Capital Standards. A Revised Framework. Comprehensive Version, Basel, Switzerland: Bank for International Settlements, 2006.

M. G. Cruz, Modeling, Measuring and Hedging Operational Risk, London: Wiley, 2002.

C. Alexander, Operational Risk: Regulation, Analysis and Management, Harlow, England: Pearson Education Ltd, 2003.

P. V. Shevchenkо, Modeling Operational Risk Using Bayesian Inference, New York: Springer, 2011.

S. O. Dmytrov, Modeling of operational risk assessment of a commercial bank, Sumy, Ukraine: SHEI “Ukrainian Academy of Banking”, 2010.

A. Frachot, P. Georges, and T. Roncalli, “Loss distribution approach for operational risk,” SSRN Electron. J., pp. 56–99, 2001. doi: 10.2139/ssrn.1032523.

С. Alexander, “Bayesian methods for measuring operational risk,” SSRN Electron. J., pp. 45–65, 2000. doi: 10.2139/ssrn.248148.

Х. Hao, “Operational risk control of commercial banks based on Bayesian network,” Proc. 2013 ICETIS, 2013, pp. 913–918. doi: 10.2991/icetis-13.2013.209.

Yongqi Yang, Wanlei Xue, Chaoyuan Li, Xin Zhao, and Nan Xu, “An AHP-Bayesian model for operational risk evaluation of integrated energy systems,” IOP Conf. Ser. Materials Sci. Eng., vol. 484, pp. 1–8, 2019. doi: 10.1088/1757-899X/484/1/012052.

Y. K. Yoon, “Modeling operational risk in financial institutions using Bayesian networks”, J. Risk Insur., UK, №74(4), pp. 795–827, 2007.

M. Neil, N. Fenton, and M. Tailor, “Using Bayesian networks to model expected and unexpected operational losses,” Risk Analysis, vol. 25, no. 4, pp. 963–972, Aug. 2005. doi: 10.1111/j.1539-6924.2005.00641.x.

A. Stuart and K. Ord, Kendalls Advanced Theory of Statistics, vol. 1, Wiley, 1994.

S. Figini, L. Gao and P. Giudici, “Bayesian operational risk models,” J. Oper. Risk, vol. 10, no. 2, pp. 45–60, 2015. doi: 10.21314/JOP.2015.155

C. K. Chow and C. N. Liu, “Approximating discrete probability distributions with dependence trees,” IEE Trans. Inf. Theory, vol. 14, pp. 462–467, 1968.

T. Minka et al. (2014). Infer.NET 2.6 Microsoft Research Cambridge [Online]. Available: http://research.microsoft.com/infernet

M. Neil, D. Hager and L. B. Andersen, “Modeling operational risk in financial institutions using hybrid,” J. Oper. Risk, vol. 4, no. 1, pp. 1–28, 2009.

Downloads

Published

2021-12-15

Issue

No. 3 (2021)

Section

Статті

License

Copyright (c) 2021 Liudmyla B. Levenchuk, Vira G. Huskova, Petro I. Bidyuk

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

The ownership of copyright remains with the Authors.
 
Authors may use their own material in other publications provided that the Journal is acknowledged as the original place of publication and National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” as the Publisher.

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under CC BY 4.0 that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work