Biryukov A.N.Sterlitamak Branch of Bashkir State University, Sterlitamak, Republic of Bashkortostan, Russian Federation guzsa@ufamts.ru
The research aims at building clustering models of taxpaying entities for tax administration purposes. Furthermore, the author considers the clustering model as a tool to support the financial regulator during the decision-making process concerning credit risks. Prompt and flexible tax administration is a part of the public tax management. If effectively performed, the task will contribute to an increase in budget replenishment at each particular level, on the one hand, and preserve the economic stability of taxpaying entities, on the other hand. The objective of the author's study is to articulate correct managerial decisions concerning the objectives mentioned. The methods of the study require quite accurate knowledge of taxpayers' financial and economic condition. The objective of the study is to find out how it would be possible to test and detect the unfavorable business development trends, i.e. bankruptcy threats, at the earliest stages, using multiple economic indicators available to tax authorities. The result of this computational experiment may constitute the corpus of tax returns for any previous period of time in respect of multiple tax items, which are interesting for the analyst. Based on the model, taxpayers can be classified by cluster for purposes of the above objective. Managerial decisions on tax administration will be more effective provided that public budget interests and the taxpaying entities' economic stability are concurrently respected and observed, when, as a result of the experiment, the regulator will have reliable information about the presence of a specific entity in one of the clusters mentioned in the objective. Correct decisions about tax administration are crisis management tools. Many bankruptcy forecast models firmly demonstrate that they can be used to provide forecasts for ex post classification purposes. In the current crisis circumstances, when survival reserves and credit reserves are mutually related, those models are ineffective. Therefore, it is relevant to elaborate new models for credit risk assessment, which could be used as an unbiased and scientific basis in order to take decisions on granting anti-crisis loans, tax benefits and tax holidays, etc.
Biryukov A.N. Teoreticheskie osnovy razrabotki neirosetevykh modelei v sisteme nalogovogo administrirovaniya [The theoretical basis of the development of neural network model in the system of tax administration]. Ufa, Gilem Publ., 2011, 380 p.
Biryukov A.N. Ispol'zovanie metoda kombinirovannogo podkhoda v modelirovanii sistemy nalogovogo administrirovaniya [The use of the combined approach in modeling the tax administration system]. Ekonomika i upravlenie = Economics and Management, 2011, no. 4, pp. 93–97.
Biryukov A.N. Obobshchenie metoda vlozhennykh matematicheskikh modelei na osnove baiesovskogo podkhoda k regulyarizatsii zadach neirosetevogo modelirovaniya nalogovogo i finansovogo kontrolya [Summary of the nested model method based on the Bayesian approach to regulate neural network modeling of the tax and financial control]. Ekonomika i upravlenie = Economics and Management, 2010, no. 1, pp. 85–89.
Biryukov A.N. Neirosetevaya model' ranzhirovaniya i kontrolya deklaratsii nalogoplatel'shchikov [Neural network model for ranking and control of taxpayers' tax returns]. Ekonomika i upravlenie = Economics and Management, 2010, no. 11, pp. 106–110.
Biryukov A.N. Ekonomiko-matematicheskaya model' upravleniya riskami s primeneniem imitatsionnogo modelirovaniya [Economic-mathematical model of risk management with the use of simulation]. Available at: Link. (In Russ.)
Biryukov A.N. Baiesovskaya regulyarizatsiya neirosetevykh modelei ranzhirovaniya i klasterizatsii ekonomicheskikh ob"ektov [Bayesian regularization of neural network models for ranking and clustering of economic objects]. Ufa, Gilem Publ., 2011, 292 p.
Bublik N.D., Golichev I.I., Gorbatkov S.A., Smirnov A.V. Teoreticheskie osnovy razrabotki tekhnologii nalogovogo kontrolya i upravleniya [Theoretical bases of development of technology of tax control and management]. Ufa, BashSU Publ., 2004, 335 p.
Baestaens D.-E., Van den Bergh V.-M., Wood D. Neironnye seti i finansovye rynki: prinyatie reshenii v torgovykh operatsiyakh [Neural Network Solutions for Trading in Financial Markets]. Moscow, TVP Publ., 1998, 254 p.
Gorbatkov S.A., Polupanov D.V. Metody neiromatematiki v nalogovom kontrole [Neural mathematic methods of tax control]. Ufa, BashSU Publ., 2008, 134 p.
Gorbatkov S.A., Polupanov D.V., Biryukov A.N., Makeeva E.Yu. Metodologicheskie osnovy razrabotki neirosetevykh modelei ekonomicheskikh ob"ektov v usloviyakh neopredelennosti [Methodological basis for development of neural network models of economic objects in conditions of uncertainty]. Moscow, Ekonomicheskaya gazeta Publ., 2012, 494 p.
Ezhov A.A., Shumskii S.A. Neirokomp'yuting i ego primenenie v ekonomike i biznese [Neural computing and its application in economy and business]. Moscow, MEPhI Publ., 1998, 224 p.
Kallan R. Osnovnye kontseptsii neironnykh setei [Basic concepts of neural networks]. Moscow, Vil'yams Publ., 2001, 287 p.
Kuznetsov Yu.A., Perova V.I. Ispol'zovanie neirosetevogo modelirovaniya v analize deyatel'nosti krupneishikh kompanii Rossiiskoi Federatsii [The use of neural network modeling in the analysis of activities of the largest companies in the Russian Federation]. Ekonomicheskii analiz: teoriya i praktika = Economic Analysis: Theory and Practice, 2010, no. 31, pp. 32–42.
Kuznetsov Yu.A., Perova V.I., Vorob'eva E.V. Neirosetevoe modelirovanie finansovo-ekonomicheskoi deyatel'nosti krupneishikh kompanii Povolzh'ya [Neural network modeling of the financial and economic activities of the largest companies in the Volga Region]. Ekonomicheskii analiz: teoriya i praktika = Economic Analysis: Theory and Practice, 2011, no. 35, pp. 25–36.
Kuznetsov Yu.A., Perova V.I., Eivazova E.N. Neirosetevoe modelirovanie dinamiki innovatsionnogo razvitiya regionov Rossiiskoi Federatsii [Neural network modeling of the innovative development dynamics of regions of the Russian Federation]. Regional'naya ekonomika: teoriya i praktika = Regional Economics: Theory and Practice, 2014, no. 4, pp. 18–28.
Mishustin M.V. Mekhanizm gosudarstvennogo nalogovogo administrirovaniya v Rossii [The mechanism of the State tax administration in Russia]. Moscow, Finansy i statistika Publ., 2003, 230 p.
Khaikin S. Neironnye seti: polnyi kurs [Neural networks: a complete course]. Moscow, Vil'yams Publ., 2006, 1104 p.
Yasnitskii L.N. Vvedenie v iskusstvennyi intellekt [Introduction to artificial intelligence]. Moscow, Akademiya Publ., 2010, 176 p.
Yasnitskii L.N., Bondar' V.V., Burdin S.N. Permskaya nauchnaya shkola iskusstvennogo intellekta i ee innovatsionnye proekty [The Perm School of artificial intelligence and innovative projects]. Moscow, Izhevsk, Regulyarnaya i khaoticheskaya dinamika Publ., 2008, 75 p.
Argenti J. Corporate Collapse: The Causes and Symptoms. McGraw-Hill book Company (UK) limited, 1976.
