TY - JOUR AU - Gorbatkov, S. A. AU - Rastegaeva, F. S. AU - Farkhieva, S. A. AU - Nakonechnaya, T. V. AU - Sheina, A. U. PY - 2019/12/29 Y2 - 2024/03/29 TI - A dynamic model of corporate bankruptcies with a combination of structural synthesis of the neural network and the regularization of its training JF - Revista de la Universidad del Zulia JA - Revista de la Universidad del Zulia VL - 10 IS - 28 SE - Artículos DO - UR - https://produccioncientificaluz.org/index.php/rluz/article/view/30631 SP - 185-199 AB - 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. ER -