<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">finance</journal-id><journal-title-group><journal-title xml:lang="ru">Финансы: теория и практика/Finance: Theory and Practice</journal-title><trans-title-group xml:lang="en"><trans-title>Finance: Theory and Practice</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2587-5671</issn><issn pub-type="epub">2587-7089</issn><publisher><publisher-name>Financial University under The Government of Russian Federation</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.26794/2587-5671-2018-22-3-112-123</article-id><article-id custom-type="elpub" pub-id-type="custom">finance-662</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ФИНАНСОВАЯ БЕЗОПАСНОСТЬ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>FINANCIAL SECURITY</subject></subj-group></article-categories><title-group><article-title>НЕЙРОСЕТЕВАЯ МОДЕЛЬ ДИАГНОСТИКИ СТАДИЙ РАЗВИВАЮЩЕГОСЯ БАНКРОТСТВА КОРПОРАЦИЙ</article-title><trans-title-group xml:lang="en"><trans-title>NEURAL NETWORK MODEL OF DIAGNOSTICS OF STAGES OF DEVELOPING CORPORATE BANKRUPTCY</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-7752-8431</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname> Горбатков</surname><given-names>С. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Gorbatkov</surname><given-names>S. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>доктор технических наук, профессор, заслуженный деятель науки Республики Башкортостан, профессор кафедры «Математика и информатика», </p><p>Уфа</p></bio><bio xml:lang="en"><p>Dr. Sci. (Engin.), Professor, Honored worker of science of the Republic of Bashkortostan, Professor of the Department of “Mathematics and Informatics”, </p><p>Ufa</p></bio><email xlink:type="simple">SAGorbatkov@fa.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-2556-2785</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname> Фархиева</surname><given-names>С. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Farkhieva</surname><given-names>S. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>кандидат технических наук, заведующая кафедрой «Математика и информатика», </p><p>Уфа</p></bio><bio xml:lang="en"><p>Cand. Sci. (Engin.), Head of the Department of “Mathematics and Informatics”, </p><p>Ufa</p></bio><email xlink:type="simple">SAFarhieva@fa.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Уфимский филиал Финансового университета</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Ufa branch of the Financial University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2018</year></pub-date><pub-date pub-type="epub"><day>10</day><month>06</month><year>2018</year></pub-date><volume>22</volume><issue>3</issue><fpage>112</fpage><lpage>123</lpage><permissions><copyright-statement>Copyright &amp;#x00A9;  Горбатков С.А.,  Фархиева С.А., 2018</copyright-statement><copyright-year>2018</copyright-year><copyright-holder xml:lang="ru"> Горбатков С.А.,  Фархиева С.А.</copyright-holder><copyright-holder xml:lang="en">Gorbatkov S.A., Farkhieva S.A.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://financetp.fa.ru/jour/article/view/662">https://financetp.fa.ru/jour/article/view/662</self-uri><abstract><p>В статье исследуется проблема разработки информационно-математической модели для поддержки принятия решений по реструктуризации кредитной задолженности корпораций в банковских технологиях финансового менеджмента.</p><p>Цель статьи — создание модели, позволяющей диагностировать стадии развивающегося кризиса корпораций в сложных условиях неполноты и зашумленности данных. Модель должна служить инструментом повышения объективности и качества принимаемых решений по реструктуризации кредитной задолженности корпораций. Исследование проводилось на основе нейросетевых методов моделирования и системного анализа, методов теории принятия решений, решения обратных задач интерпретации, т.е. извлечения новых знаний из данных. Разработан оригинальный метод построения нейросетевой логистической модели банкротств (НЛМБ) в сложных условиях моделирования. Новыми признаками метода, увеличивающими прогностическую силу модели, являются: 1) оптимальный отбор факторов с помощью байесовского ансамбля вспомогательных нейросетей, осуществляющих компрессию факторного пространства; 2) ступенчатая компрессия факторов на основе обобщенной функции желательности Харрингтона; 3) регуляризация основной (рабочей) нейросетевой модели на байесовском ансамбле нейросетей. НЛМБ апробирована на реальных данных корпораций строительной отрасли. Число верно идентифицированных объектов на тестовом множестве составило более 90% на всех нейросетях ансамбля.</p><p>В НЛМБ достаточно высокое прогностическое качество нейросетевой модели обеспечивается новыми признаками метода и порождает эмерджентный эффект, проверенный в вычислительных экспериментах: улучшение качества нейросетевой модели по критерию правильно идентифицированных объектов Θ составляет 3,336 раза при компрессии факторов в 1,35 раза. НЛМБ может быть распространен на широкий круг задач финансового менеджмента. </p></abstract><trans-abstract xml:lang="en"><p>The article deals with the problem of developing an information and mathematical model to support decisionmaking on the restructuring of corporate debt in the banking technologies of financial management. The purpose of the article is to create a model that allows diagnostic of the stages of developing corporate crisis in difficult conditions of incomplete and noisy data. The model should serve as a tool for improving the objectivity and quality of decisions on the restructuring of corporate debt. The study was conducted on the basis of neural network modelling and system analysis methods, methods of decision-making theory, a solution of inverse problems of interpretation, i.e. extraction of new knowledge from data. We developed an original method of constructing neural network logistic model of bankruptcies (NNLMB) in the difficult conditions of the simulation. New features of the method, increasing the predictive power of the model, are: 1) optimal selection of factors using Bayesian ensemble of auxiliary neural networks, performing compression of factor space; 2) step compression of factors based on the generalized Harrington desirability function; 3) regularization of the main (working) neural network model on Bayesian ensemble of neural networks. NNLMB is tested on real data from corporations of the construction industry. The number of correctly identified objects on the test set was more than 90% on all neural networks of the ensemble. In NNLMB, a sufficiently high prognostic quality of the neural network model is provided by new features of the method and generates an emergent effect, which was proven in computational experiments: the improvement of the quality of the neural network model by the criterion of correctly identified objects Θ is 3.336 times with the compression of factors by 1.35 times. NNLMB can be applied to a wide range of financial management tasks.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>нейросетевая модель</kwd><kwd>стадии развития банкротства корпораций</kwd><kwd>поддержка решений реструктуризации кредитной задолженности</kwd></kwd-group><kwd-group xml:lang="en"><kwd>neural network model</kwd><kwd>stages of development of corporate bankruptcy</kwd><kwd>support of decisions on credit debt restructuring</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Галушкин А.И. Нейронные сети: основы теории. М.: Горячая линия-Телеком; 2012. 469 с.</mixed-citation><mixed-citation xml:lang="en">Galushkin A.I. Neural networks: theory bases. Moscow: Goryachaya liniya-Telekom; 2012. 469 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Галушкин А.И. Применение нейрокомпьютеров в финансовой деятельности. URL: http://masters.donntu. org/2007/kita/bolkunevich/library/galuwkin.htm (дата обращения: 28.08.2017).</mixed-citation><mixed-citation xml:lang="en">Galushkin A.I. The use of neurocomputers in financial activity. URL: http://masters.donntu.org/2007/kita/ bolkunevich/library/galuwkin.htm (accessed 28.08.2017). (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Горбатков С.А., Полупанов Д.В., Макеева Е.Ю., Бирюков А.Н. Методологические основы разработки нейросетевых моделей экономических объектов в условиях неопределенности. М.: Изд. дом «Экономическая газета»; 2012. 494 с.</mixed-citation><mixed-citation xml:lang="en">Gorbatkov S.A., Polupanov D.V., Makeeva E. Yu., Biryukov A.N. Methodological bases of development of neural network models of economic objects in the conditions of uncertainty. Moscow: Publ. House of “Ekonomicheskaya gazeta”; 2012. 494 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Горбатков С.А., Фархиева С.А., Белолипцев И.И. Нейросетевые и нечеткие методы моделирования диагностики и прогнозирования банкротств корпораций. М.: Прометей; 2018. 371 с.</mixed-citation><mixed-citation xml:lang="en">Gorbatkov S.A., Farkhieva S.A., Beloliptsev I.I. Neural network and fuzzy methods for modeling corporate bankruptcy diagnostics and forecasting. Moscow: Prometheus; 2018. 371 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Белолипцев И.И., Горбатков С.А., Романов А.Н., Фархиева С.А. Моделирование управленческих решений в сфере экономики в условиях неопределенности. М.: Инфра-М; 2015. 299 с.</mixed-citation><mixed-citation xml:lang="en">Beloliptsev I.I., Gorbatkov S.A., Romanov A.N., Farkhieva S.A. Modeling of managerial decisions in the sphere of economy in the conditions of uncertainty. Moscow: Infra-M; 2015. 299 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Тихонов А.Н., Арсенин В.Я. Методы решения некорректных задач. М.: Наука: Физматлит; 1986. 288 с.</mixed-citation><mixed-citation xml:lang="en">Tikhonov A.N., Arsenin V. Ya. Methods for solving incorrect problems. Moscow: Nauka: Fizmatlit; 1986. 288 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Rissanen J. Modeling by shortest data description. Automatica. 1978;14(5):465–471. DOI: 10.1016/0005– 1098(78)90005–5</mixed-citation><mixed-citation xml:lang="en">Rissanen J. Modeling by shortest data description. Automatica. 1978;14(5):465–471. DOI: 10.1016/0005– 1098(78)90005–5</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Доленко С.А.Нейросетевые методы решения обратных задач. XVВсеросс. науч.-техн. конф. «Нейроинформатика 2013»: Лекции по нейроинформатике (г.Москва, 21–25 января 2013 г.). М.: НИЯУ МИФИ; 2013:214–269.</mixed-citation><mixed-citation xml:lang="en">Dolenko S.A. Neural network methods for solving inverse problems. In: 15th All-Russ. sci.-techn. conf. “Neuroinformatics –2013”: Lectures on neuroinformatics (Moscow, 21–25 Jan. 2013). Moscow: NRNU MEPhI; 2013:214–269. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Адлер Ю.П., Маркова Е.В., Грановский Ю.В. Планирование эксперимента при поиске оптимальных условий. М.: Наука; 1976. 279 с.</mixed-citation><mixed-citation xml:lang="en">Adler Yu.P., Markova E.V., Granovskii Yu.V. Planning an experiment in the search for optimal conditions. Moscow: Nauka; 1976. 279 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Горский В.Г., Адлер Ю.П. Планирование промышленных экспериментов. М.: Металлургия; 1974. 112 с.</mixed-citation><mixed-citation xml:lang="en">Gorskii V.G., Adler Yu.P. Planning of industrial experiments. Moscow: Metallurgiya; 1974. 112 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Давыдова Г.В., Беликов А.Ю. Методика количественной оценки риска банкротства предприятий. Управление риском. 1999;(3):13–20.</mixed-citation><mixed-citation xml:lang="en">Davydova G.V., Belikov A. Yu. Technique of quantitative assessment of the risk of bankruptcy of enterprises. Upravlenie riskom. 1999;(3):13–20. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Altman E.I., Marco G., Varetto F.Corporate distress diagnosis: Comparisons using linear discriminant analysis and neural network (the Italian experience). Journal of Banking and Finance. 1994;18(3):505–529. DOI: 10.1016/0378– 4266(94)90007–8</mixed-citation><mixed-citation xml:lang="en">Altman E.I., Marco G., Varetto F.Corporate distress diagnosis: Comparisons using linear discriminant analysis and neural network (the Italian experience). Journal of Banking and Finance. 1994;18(3):505–529. DOI: 10.1016/0378– 4266(94)90007–8</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Cho S., Kim J., Bae J.K.An integrative model with subject weight based on neural network learning for bankruptcy prediction. Expert Systems with Applications. 2009;36(1):403–410. DOI: 10.1016/j.eswa.2007.09.060</mixed-citation><mixed-citation xml:lang="en">Cho S., Kim J., Bae J.K.An integrative model with subject weight based on neural network learning for bankruptcy prediction. Expert Systems with Applications. 2009;36(1):403–410. DOI: 10.1016/j.eswa.2007.09.060</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Udo G. Neural network performance on the bankruptcy classification problem. Computers and Industrial Engineering. 1993;25(1–4):377–380. DOI: 10.1016/0360–8352(93)90300-M</mixed-citation><mixed-citation xml:lang="en">Udo G. Neural network performance on the bankruptcy classification problem. Computers and Industrial Engineering. 1993;25(1–4):377–380. DOI: 10.1016/0360–8352(93)90300-M</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Ohlson J.A. Financial ratios and the probabilistic prediction of bankruptcy. Journal of Accounting Research. 1980;18 (1):109–131. DOI: 10.2307/2490395</mixed-citation><mixed-citation xml:lang="en">Ohlson J.A. Financial ratios and the probabilistic prediction of bankruptcy. Journal of Accounting Research. 1980;18 (1):109–131. DOI: 10.2307/2490395</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Altman E.I. Corporate financial distress: A complete guide to predicting, avoiding, and dealing with bankruptcy. New York: Wiley-Interscience Publ.; 1983. 368 p.</mixed-citation><mixed-citation xml:lang="en">Altman E.I. Corporate financial distress: A complete guide to predicting, avoiding, and dealing with bankruptcy. New York: Wiley-Interscience Publ.; 1983. 368 p.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Шумский С.А. Байесова регуляризация обучения. Науч. сессия МИФИ 2002. IV Всеросс. науч.-техн. конф. «Нейроинформатика 2002»: Лекции по нейроинформатике (г. Москва, 23–25 января 2002 г.). Ч. 2. М.: НИЯУ МИФИ; 2002:30–93. URL: http://neurolectures.narod.ru/2002/Shumsky 2002.pdf (дата обращения: 18.05.2018).</mixed-citation><mixed-citation xml:lang="en">Shumsky S.A. Bayesian regularization of learning. In: Sci. session of MEPhI 2002. 4th All-Russ. sci.-techn. conf. “Neuroinformatics — 2002”: Lectures on neuroinformatics (Moscow, 23–25 Jan. 2002). Pt. 2. Moscow: NRNU MEPhI; 2002:30–93. URL: http://neurolectures.narod.ru/2002/Shumsky 2002.pdf (accessed 18.05.2018). (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">MacKay D. Bayesian interpolation. Neural Computation. 1992;4(3):415–447. DOI: 10.1162/neco.1992.4.3.415</mixed-citation><mixed-citation xml:lang="en">MacKay D. Bayesian interpolation. Neural Computation. 1992;4(3):415–447. DOI: 10.1162/neco.1992.4.3.415</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">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;3(1):65–76.</mixed-citation><mixed-citation xml:lang="en">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;3(1):65–76.</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Шевченко И.В., Халафян А.А., Васильева Е.Ю. Создание виртуальной клиентской базы для анализа кредитоспособности российских предприятий. Финансы и кредит. 2010;(1):13–18.</mixed-citation><mixed-citation xml:lang="en">Shevchenko I.V., Khalafyan A.A., Vasil’eva E.Yu. Development of virtual client base for the analysis of solvency of Russian enterprises. Finansy i kredit = Finance and Credit. 2010;(1):13–18. (In Russ.).</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
