Probabilistic-Statistical Method for Risk Assessment of Financial Losses

Authors

DOI:

https://doi.org/10.20535/1810-0546.2018.2.128989

Keywords:

Financial risks, Kalman filter, Bayesian network, Regression model, Assessment of financial losses

Abstract

Background. Financial risks various fields of human activities may experience are associated with a large number of uncertainties, fuzziness, incompleteness and inaccuracy of data. To predict financial losses of companies, even such data need to be processed, so the task of developing a new method, which will filter incoming data and predict financial losses, is quite relevant.

Objective. The aim of the paper is to develop a new method for assessing the risk of potential financial losses and propose a comprehensive probabilistic-statistical model on its basis.

Methods. The following comprehensive methods were applied: optimal filter, for data pre-processing and preparation for model construction, regression model for formal description and prediction of conditional variance and probabilistic model in the form of Bayesian network for estimation of probability for possible losses.

Results. Proposed model was used to assess financial market risk of transactions with the stock market. The used statistical data describes evolution of stock prices for well-known companies. As a result of computational experiments it was found that the quality of short-term forecasts of volatility improves by an average from 7.1 to 50 % due to optimal data filtering. Application of the model constructed in the form of Bayesian network provided an opportunity for further improvement of probabilistic estimates for possible financial losses in the course of trading transactions at the stock market.

Conclusions. The risk assessment of financial losses is an urgent task that can be solved by different methods. The proposed probabilistic statistical method for the probabilistic estimation of possible financial losses in the course of trading operations in the stock market was effective, therefore, in the future it will be expanded to cover its application to other types of financial risks.

Author Biographies

Petro I. Bidyuk, Igor Sikorsky Kyiv Polytechnic Institute

Петро Іванович Бідюк

Nataliia V. Kuznietsova, Igor Sikorsky Kyiv Polytechnic Institute

Наталія Володимирівна Кузнєцова

References

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

Handbook of Credit Scoring, E. Mays, Ed. Chicago: Glenlake Publishing Company, Ltd., 2001.

O.M. Trofymchuk et al., “Decision support system for implementing systemic approach to forecasting”, Int. J. Comp. Technol., vol. 14, no. 5, pp. 5769–5778, 2015.

N. Kuznietsova and P. Bidyuk, “Modeling financial risks in telecommunication field”, Naukovi Visti NTUU KPI, no. 5, pp. 51–58, 2017. doi: 0.20535/1810-0546.2017.5.110338

A.J. McNeil et al., Quantitative Risk Management. Princeton: Princeton University Press, 2005, 538 p.

P.I. Bidyuk and O.Ye. Matros, “Models for clients credit risk estimation”, Cybernetics and Computations, vol. 153, pp. 87–95, 2008.

W.R. Gilks et al., Markov Chain Monte Carlo in Practice. New York: Chapman & Hall/CRC, 2000, 486 p.

N.V. Kuznietsova, “Information technologies for clients’ database analysis and behaviour forecasting”, in Selected Papers of the XVII Int. Sci. Practical Conf. Inform. Technol. Security (ITS 2017), 2017, vol. 2067, pp. 56–62 [Online]. Available: http://ceur-ws.org/Vol-2067

F. Burstein and C.W. Holsapple, Handbook of Decision Support Systems. Berlin: Springer-Verlag, 2008, 908 p.

C.W. Hollsapple and A.B. Winston, Decision Support Systems. Saint Paul: West Publishing Company, 1996, 860 p.

P.I. Bidyuk et al., Methods of Forecasting. Lugansk: Alma Mater, 2008, 608 p.

K. Murphy. (2007). A Brief Introduction to Graphical Models and Bayesian Networks [Online]. Available: http://www.cs.ubc.ca/~murphyk/Bayes/bayes.html

U. Kjærulff, “dHugin: A computational system for dynamic time-sliced Bayesian networks”, Int. J. Forecasting, vol. 11, no. 1, pp. 89–111, 1995. doi: 10.1016/0169-2070(94)02003-8

W.M. Bolstad, Understanding Computational Bayesian Statistics. Hoboken: John Wiley & Sons, Ltd, 2010, 334 p.

Published

2018-06-12

Issue

Section

Art