Evaluation of the sensitivity of neural network method for constructing the dynamic model of bankruptcy to identify signs of a developing process of the crisis of the Corporation

ПОДЕЛИТЬСЯ С ДРУЗЬЯМИ
Authors


Doctor of Technical Sciences, Professor Mathematics and Computer Science
Russia, Financial University under the Government of the Russian Federation
sgorbatkov@mail.ru


graduate student of macroeconomic development and public administration
Russian, Bashkir State University
liankakasimva@yandex.ru


graduate student of the department of electrical equipment and automation of industrial enterprises
Russia, Ufa State Oil Technical University
irikfarvaev@yandex.ru

Abstract

Pilot original neural network logistic dynamic method of building the model of bankruptcies. Investigated the convergence of the iterations of the restoration indicator bankruptcy on incomplete data, which makes the basic "core" of the proposed method and regularization model on Bayesian ensemble of neural networks. Compared with 22 known models of bankruptcies: MDA models, logit models, expert models, rating models, regulated by the method of the Government of the Russian Federation. 

Keywords

Dynamic neural network method, the model of an evolving bankruptcy, convergence, regularization, evaluation of the sensitivity of the method, the prediction of bankruptcy, comparison with known methods. 

Рекомендуемая ссылка

Gorbatkov Stanislav Anatol'evich , Kasimova Liana Irikovna , Farvaev Irik Rafitovich
Evaluation of the sensitivity of neural network method for constructing the dynamic model of bankruptcy to identify signs of a developing process of the crisis of the Corporation// Современные технологии управления. ISSN 2226-9339. – #11 (59). Номер статьи: 5902. Дата публикации: . Режим доступа: http://sovman.ru/en/article/5902/

Full article text is available only in Russian.
Please select from the menu Russian language and continue reading.


References

  1. Makeeva E.YU., Gorbatkov S.A., Belolipcev I.I. Models of diagnostic bankruptcies organizations [O modelyah diagnostiki bankrotstv organizacij]. Management and Business  Administration. 2014. №1. pp. 151-171.
  2. Polupanov D.V., Gorbatkov S.A., Saetova G. D., Kasimova L.I. A study of the convergence rate of the iterative dynamic neural network risk assessment method bankruptcy [Issledovanie skorosti shodimosti iteracionnogo nejrosetevogo dinamicheskogo metoda ocenki riska bankrotstva]. Mathematical methods and models in the study of public and financial markets: Proceedings of the All-Russian Youth Scientific Practical Conference (April 27-28, 2015 in Ufa). In 3 parts. Part II. Ufa Aeterna. 2015. pp. 142-146.
  3. Galushkin A. I. The theory of neural networks [Teorija nejronnyh setej]. Bk. 1 Proc. manual for schools.  M . IPRZH, 2000. 416 p.
  4. Tihonov A. N., Arsenin V. Ja. Methods of solving ill-posed problems, monograph [Metody reshenija nekorrektnyh zadach. Monografija]. Ed. 2nd.  M . Nauka. Home edition of Physical and mathematical literature, 1979.  286 p.
  5. Shumskij S.A. Bayesian regularization training [Bajesova reguljarizacija obuchenija]. Lectures for school seminar Modern problems of neuroinformatics (23-25 January 2002). M. MiFi 2002 (file: //NeyroOKIntelsoft.htm) p. 33.
  6. Gorbatkov S. A., Polupanov D. V., Makeeva E. Ju., Birjukov A. N. The methodological basis for the development of neural network models of economic facilities in the face of uncertainty, monograph [Metodologicheskie osnovy razrabotki nejrosetevyh modelej jekonomicheskih ob#ektov v uslovijah neopredelennosti. Monografija]. M . Publishing house Economic newspaper, 2012. 494 p.
  7. Gorbatkov S. A., Belolipcev I. I., Makeeva E. Ju. The choice of economic indicators for the diagnosis and prediction of failures based on the Bayesian approach and intelligent information technologies  [Vybor sistemy jekonomicheskih pokazatelej dlja diagnostiki i prognozirovanija bankrotstv na osnove bajesovskogo podhoda i intellektual’nyh informacionnyh tehnologij ]. Bulletin of the Financial University under the Government of the Russian Federation.  2013.  №4 (76). pp. 50-62.
  8. Nedosekin A.O. Methodological bases of modeling of financial activity using fuzzy-multiple descriptions [Metodologicheskie osnovy modelirovanija finansovoj dejatel’nosti s ispol’zovaniem nechetko-mnozhestvennyh opisanij]. Diss. on soisk. a scientific degree of the doctor ehkon. Sciences.  St. Petersburg. St. Petersburg gov’t. University of Economics and Finance, 2003. 280 p.
  9. Zhdanov V,Ju., Zhdanov I.Ju., QFinAnalysis. Version 1.9 [QFinAnalysis. Versija 1.9]. School Financial Analysis [Official site]. URL: // www. beintrend.ru/qfinanalysisfree,2011