FORECASTING THE RETURN OF THE LOAN PORTFOLIO ON THE BASIS OF MARKOV MODEL
DOI:
https://doi.org/10.14529/mmp170305Keywords:
, paymentffows, Markov chain, loan portfolio, forecastingAbstract
We consider the problem of mathematical modelling of ows of loan portfolio payments. We assume that the change in the quality of each loan is described by a simple Markov chain with a nite number of states. In this case, the ow of loan payments is a random process, which depends on the Markov chain. On the basis of the proposed model and known relations of the stochastic systems theory, we describe the expected ows of payments of the entire loan portfolio and construct a method to forecast the expected return (net present value) of the portfolio. We analyze an accuracy of the obtained model and a sensitivity of net present value of the portfolio to a change in the transition probabilities in the Markov chainReferences
Gupton, G.M. CreditMetrics - Technical Document / G.M. Gupton, C.C. Finger, M. Bhatia. - N.Y.: J.P. Morgan and Co., 1997.
Schuermann, T. Credit Migration Matrices / T. Schuermann // Encyclopedia of Quantitative Risk Assessment. - N.Y.: John Wiley & Sons, 2008.
Fantazzini D. [Credit Risk Management]. Applied Econometrics, 2008, vol. 4, no. 12, pp. 105-138. (in Russian)
Jones, M.T. Estimating Markov Transition Matrices Using Proportions Data: An Application to Credit Risk // International Monetary Fund Working Paper. - 2005. - WP-05-219.
Jafry, Y. Measurement, Estimation and Comparison of Credit Migration Matrices / Y. Jafry, T. Schuermann // Journal of Banking & Finance. - 2004. - V. 28. - P. 2603-2639.
Anderson, T.W. Statistical Inference about Markov Chains / T.W. Anderson, L.A. Goodman // Annals of Mathematical Statistics. - 1957. - V. 28. - P. 89-110.
Kiefer, N.M. A Simulation Estimator for Testing the Time Homogeneity of Credit Rating Transitions / N.M. Kiefer, C.E. Larson // Journal of Empirical Finance. - 2007. - V. 14. - P. 818-835.
Quirini, L. Creditworthiness Dynamics and Hidden Markov Models / L. Quirini, L. Vannucci // Journal of the Operational Research Society. - 2014. - V. 65, № 3. - P. 323-330.
Kaniovski, Y.M. Risk Assessment for Credit Portfolios: A Coupled Markov Chain Model / Y.M. Kaniovski, G.Ch. Pflug // Journal of Banking & Finance. - 2007. - V. 31. - P. 2303-2323.
Thyagarajan V., Saiful M. Retail Banking Loan Portfolio Equilibrium Mix: A Markov Chain
Model Analysis. American Journal of Applied Science, 2005, vol. 2, no. 1, pp. 410-419. DOI: 10.3844/ajassp.2005.410.419
Zhuravel' Ju.Ju. [Topical Issues of Loan Portfolio Reservation]. Bankovskij Ritejl, 2007, no. 4, pp. 21-36. (in Russian)
Nasel'skiy S.P., Jakimenko D.V. Calculation of the Size of Retail Loan Portfolio Reserves of Commercial Bank. Vestnik Sankt-Peterburgskogo Universiteta Gosudarstvennoy Protivopozharnoy Sluzhy MChS Rossii, 2009, no. 2, pp. 139-143. (in Russian)
Bronshtein E.M. [Optimization of the Time Structure of an Investment Project]. Sibirskii
zhurnal industlial'noi matematiki [Journal of Applied and Industrial Mathematics], 2005,
vol. 8, no. 1, pp. 17-29. (in Russian)
de Andrade F.W.M., Thomas L. Structural Models in Consumer Credit. European Journal
of Operational Research, 2007, vol. 183, pp. 1569-1581. DOI: 10.1016/j.ejor.2006.07.049
Kurzhanskii A.B., Furasov V.D. Identication of Bilinear Systems. Guaranteed
Pseudoellipsoidal Estimates. Automation and Remote Control, 2000, vol. 61, no. 1, pp. 38-49.
Zav'yalova T.V., Kats I.Ya., Timofeeva G.A. Stochastic System with a Ramdom Jump in Phase Trajectoty: Stability of Their Motion. Automation and Remote Control, 2002, vol. 63, no. 7, pp. 1070-1079. DOI: 10.1023/A:1016102730151
Nikonov O.I., Timofeev N.A. [Cash Flows of the Loan Portfolio under Condition of Uncertainty]. Bulletin of Ural Federal University. Series: Economics and Management, 2013, no. 2, pp. 106-111. (in Russian)
