Application of multiparametric machine learning methods for selection of significant quantitative characteristics of enterprises in the regions of the Russian Federation in the analysis of subsidisation
Keywords:
machine learning methods, statistics, data science, economic indicators, subsidised regions, subjects of the Russian FederationAbstract
In this paper, we present an original method for searching a connection between financial-economic characteristics and the subsidisation of the regions of the Russian Federation. The dataset contained data on enterprises and organisations, as well as indicators related to fixed assets, as the most significant in terms of the regions’ needs for subsidies. Two groups of regions were identified: regions with high subsidies and regions without them. Machine learning methods were used to establish differences in the reporting data of enterprises and organisations, as well as fixed assets, in the identified groups. In 2020, the most important indicators by which the groups differed from each other were the number and turnover of organisations, the balanced financial result (difference of profit and loss), the share of unprofitable organisations, accounts payable and receivable of organisations, overdue wage arrears per employee, the number of small enterprises per 10 000 people, etc. This approach (classification using optimally reliable partitioning and statistically weighted syndromes) is just beginning to be used in this area. The found dependences will allow us to more accurately outline the pattern («portrait») of each region of the Russian Federation with the possibility of further forecasting its subsidised status. A set of significant characteristics will improve the accuracy of the forecast and propose a plan for moving from the subsidised group to the group of self-sufficient subjects of the Russian Federation.
References
- Таштамиров МР, Байсаева МУ, Баташев РВ. Систематизация факторов и условий высокой дотационности региональных бюджетов. Фундаментальные исследования. 2020;11:185–192. DOI: 10.17513/fr.42896.
- Энеева МН, Ульбашева АР, Уянаева ХБ. Факторы и причины дотационности региональных экономик СКФО. Terra economicus. 2010;4(3):173 –176.
- Алимурадов МК, Мидов АЗ, Одинцов СВ. Стратегический анализ бюджетной обеспеченности высокодотационных регионов. Экономическое возрождение России. 2021;2:114 –129. DOI: 10ю37930/1990-9780-2021-2-68-113-129.
- Кричевский МЛ, Мартынова ЮА. Использование методов машинного обучения для оценки инвестиционной деятельности различных регионов России. Вопросы инновационной экономики. 2019;9(4):1557–1572. DOI: 10.18334/vinec.9.4.41432.
- Chandrinos SK, Sakkas G, Lagaros ND. AIRMS: a risk management tool using machine learning. Expert Systems with Applications. 2018;105:34 – 48. DOI: 10.1016/j.eswa.2018.03.044.
- Stanula P, Ziegenbein А, Metternich J. Мachine learning algorithms in production: a guideline for efficient data source selection. Procedia CIRP. 2018;78:261–266.
- Portugal I, Alencar P, Cowan D. The use of machine learning algorithms in recommender systems: a systematic review. Expert Systems with Applications. 2018;97:205 –227. DOI: 10.1016/j.eswa.2017.12.020.
- Борисова ЛР, Кузнецова АВ. Использование работающего компьютерного тренажера Data Master Azforus для обучения методам машинного обучения. В: Королькова ИА, редактор. Цифровая трансформация социальных и экономических систем. Материалы Международной научно-практической конференции; 28 января 2022 г.; Москва, Россия. Москва: Московский университет имени С. Ю. Витте; 2022. с. 264 –270.
- Кирилюк ИЛ, Кузнецова АВ, Сенько ОВ. Исследование взаимосвязи производственных функций и социально-экономических показателей российских регионов методом оптимальных разбиений. Информационные технологии и вычислительные системы. 2021;1:20 –31. DOI: 10.14357/20718632210103.
- Сенько ОВ, Кузнецова АВ, Воронин ЕМ, Кравцова ОА, Борисова ЛР, Кирилюк ИЛ и др. Методы интеллектуального анализа данных в исследованиях Covid-19. Журнал Белорусского государственного университета. Математика. Информатика. 2022;1:83–96. DOI: 10.33581/2520-6508-2022-1-83-96.
- Кузнецова АВ, Сенько ОВ. Возможности использования методов Data Mining при медико-лабораторных исследованиях для выявления закономерностей в массивах данных. Врач и информационные технологии. 2005;1:49 –56.
- Senko OV, Kuznetsova AV, Malygina NA, Kostomarova IV. Method for evaluating of discrepancy between regularities systems in different groups. Information Technologies & Knowledge. 2011;5(1):46 –54.
Downloads
Additional Files
Published
Issue
Section
License
Copyright (c) 2025 Journal of the Belarusian State University. Economics
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The authors who are published in this journal agree to the following:
- The authors retain copyright on the work and provide the journal with the right of first publication of the work on condition of license Creative Commons Attribution-NonCommercial. 4.0 International (CC BY-NC 4.0).
- The authors retain the right to enter into certain contractual agreements relating to the non-exclusive distribution of the published version of the work (e.g. post it on the institutional repository, publication in the book), with the reference to its original publication in this journal.
- The authors have the right to post their work on the Internet (e.g. on the institutional store or personal website) prior to and during the review process, conducted by the journal, as this may lead to a productive discussion and a large number of references to this work. (See The Effect of Open Access.)
