A dynamic model of corporate bankruptcies with a combination of structural synthesis of the neural network and the regularization of its training

  • S. A. Gorbatkov Financial University under the Government of the Russian Federation in Ufa.
  • F. S. Rastegaeva Financial University under the Government of the Russian Federation in Ufa.
  • S. A. Farkhieva Financial University under the Government of the Russian Federation in Ufa.
  • T. V. Nakonechnaya Financial University under the Government of the Russian Federation in Ufa.
  • A. U. Sheina Financial University under the Government of the Russian Federation in Ufa.
Palabras clave: neural network, optimal factor selection algorithm, conceptual basis, factor compression in clusters, Harrington function, dynamic bankruptcy model, regularization of the model integrated with structural synthesis, testing, model adequacy.

Resumen

The object of the study is the problem of financial management, in particular, the problem of forecasting the stage of developing bankruptcy of corporations-loaners and decision-making on the restructuring of credit debt. The solution of such problems is also important for assessing the solvency of counterparties in transactions, resolving issues of the illegal bankruptcies, economic security and for other areas of the economy. The subject of the research is the development of a dynamic model of bankruptcies with continuous time in conditions of high uncertainty and noise data, which allows diagnosing the stages of bankruptcy of the simulated object at any time (between the "time slices" in the data), as well as to predict the probability of bankruptcy in time ahead for a given horizon.  The purpose of the study is to create an effective mathematical tool for predicting corporate bankruptcy to support decision-making on the financial management of corporations, which is focused on complex real-world modelling conditions. On the basis of system-wide laws for reducing entropy when combining rationally interacting subsystems and the law of temporary inertia of a simulated economic object, a conceptual basis (CB) of neural network modelling of bankruptcy dynamics has been developed. The design bureau serves as a methodological basis for the proposed original neuro logistic dynamic method (NLDM), which allows us to eliminate the incompleteness and uncertainty noted in the training sample and to operate with continuous time in the procedures for diagnosing and predicting the stages of the bankruptcy of borrowing corporations.  The NLDM method, including the previously published monograph (Beloliptsev I.I., et al.) of the authors of the article, is distinguished by a new algorithm for regularizing the model integrated with the structural synthesis of the neural network.

Descargas

La descarga de datos todavía no está disponible.

Biografía del autor/a

S. A. Gorbatkov, Financial University under the Government of the Russian Federation in Ufa.

Professor of Financial University under the Government of the Russian Federation in Ufa.

F. S. Rastegaeva, Financial University under the Government of the Russian Federation in Ufa.
Professor of Financial University under the Government of the Russian Federation in Ufa.
S. A. Farkhieva, Financial University under the Government of the Russian Federation in Ufa.

Candidate of Engineering Sciences (PhD). Financial University under the Government of the Russian Federation in Ufa.

T. V. Nakonechnaya, Financial University under the Government of the Russian Federation in Ufa.
Candidate of Engineering Sciences (PhD). Financial University under the Government of the Russian Federation in Ufa.
A. U. Sheina, Financial University under the Government of the Russian Federation in Ufa.
Candidate of Engineering Sciences (PhD). Financial University under the Government of the Russian Federation in Ufa.

Citas

Beloliptsev I.I., Gorbatkow S.A., Romanov A.N., Farkhieva S.A. Modeling managerial decisions in the sphere of the economy in conditions of uncertainty: Monograph / Under the ed. Of A.N. Romanov. – М.: INFRA – М, 205-299p.

Gorbatkov S.A., FarKhieva S.A., Beloliptsev I.I. Neural network and fuzzy simulation methods for diagnostics and prediction of bankruptcies of corporations: Monograph / Under the editorship of Professor S.A. Gorbatkov. - Moscow: Prometheus, 2018.- 371p.

Gorbatkov S.A., Polupanov D.V. Optimal selection and aggregation of exogenous variables in neural network models of bankruptcies based on Harrington functions // Information Technologies. Volume 24. No. 2, 2018. - p. 121-130.

Haikin S. Neural networks: full course: textbook / 2-ed.; translated from English. – Moscow: Williams, 2006. – 1104 p.

Kobets E.A. The implementation of import substitution programme in the agricultural sector. Modern Scientist. 2017. № 2. P. 71 – 74.

Komarova S.L. The assessment of the consumer basket for the analysis of the region competitiveness. Russian Economic Bulletin. 2018. Vol. 1. Issue 2. P. 19 – 25.

Kupryushin P.A., Chernyatina G.N. Economic and environmental aspects of rational nature management and optimization of the process of import substitution in the agro-industrial complex. Modern Economy Success. 2017. № 3. P. 44 – 48.

Makeeva E.U., Neretina E.A. Binary model versus discriminant analysis relating to corporate bankruptcies: The Case of Russian Construction Industry // Journal of Accounting, Finance and Economics. 2013. Vol. 3. № 1. P. 65-76.

Milov V.R. Structural and parametric synthesis of neural network information processing systems // Author. diss. of doctor. tech. sciences. - Nizhny Novgorod, 2003. - 35 p.

Moiseenko Zh.N. State support of small forms of management in agro-industrial complex: state and development trends. Modern Economy Success. 2017. № 4. P. 12 – 17.

Narkevich L.V. Analysis of industrial capacity and break-even production in the crisis management system. Russian Economic Bulletin. 2018. Vol. 1. Issue 3. P. 28 – 41.

Ohlson J. A, Financial Ratios and the Probabilistic Prediction of Bankruptcy // Journal of Accounting Research. – 1980. - № 18(1). – P. 109-113.

Rissanen J. Modeling by shortest data description N Automatica. 1978. Vol. 14. P. 465-471.

Shumsky S.A. Bayesian regularization of training // Lectures of the school-seminar "Modern problems of neuroinformatics" (January 23-25, 2002, Moscow). - M.: MIFI, 2002. - p. 61-94.

Tikhonov A.N., Arsenin V.Ya. Methods for solving ill-posed problems: Monograph. – M.: Science. Physics and Mathematics, 1979. – 286 p.

Vernigor N.F. The system of state support of agricultural production (case study - the example of the Altai territory). Modern Economy Success. 2017. № 6. P. 7 – 10.

Publicado
2019-12-29
Cómo citar
Gorbatkov, S. A., Rastegaeva, F. S., Farkhieva, S. A., Nakonechnaya, T. V., & Sheina, A. U. (2019). A dynamic model of corporate bankruptcies with a combination of structural synthesis of the neural network and the regularization of its training. Revista De La Universidad Del Zulia, 10(28), 185-199. Recuperado a partir de https://produccioncientificaluz.org/index.php/rluz/article/view/30631