APPLICATION OF NEURAL NETWORK CLUSTER ANALYSIS METHODS IN ECONOMICS
Article Sidebar
Main Article Content
Abstract
The purpose of the study is to analyze the available methods for assessing resources in the economy and identify the most promising ones. Particular attention is paid to the processing of large amounts of information, automation of clustering and interpretation of the results obtained. Scientific novelty: the authors analyzed the advantages and disadvantages of using mathematical methods in economic analysis. As a result, the method of neural network cluster analysis was identified, which has the greatest advantages for economic analysis. Examples of the use of neural network methods in the tasks of financial analysis and risk assessment are given. The results of the work demonstrate the effectiveness of neural network approaches in comparison with traditional statistical methods. The article discusses the prospects for the further use of neural network cluster analysis in the economic sphere. The authors come to the conclusion that the use of mathematical methods in economic analysis provides an opportunity to significantly expand the toolkit for conducting research.
Article Details
References
2. Semedova K. R. Rol' ehkonomicheskogo analiza v deyatel'nosti kommercheskikh predpriyatii // Sovremennaya nauka i ee resursnoe obespechenie: innovatsionnaya paradigma: Sbornik statei Mezhdunarodnoi nauchno-prakticheskoi konferentsii, Petrozavodsk, 20 fevralya 2020 goda. – Petrozavodsk: Mezhdunarodnyi tsentr nauchnogo partnerstva «Novaya NaukA» (IP Ivanovskaya Irina Igorevna), 2020. S. 44-46.
3. Rozov N. KH., Matematicheskie rukopisi Karla Marksa, UMN, 1968, tom 23, vypusk 5. S.205–211.
4.Solopov V.A., Antsiferova O.YU., Akindinov V.V. Regulirovanie zatrat i formirovanie sebestoimosti produktsii rastenievodstva s ispol'zovaniem ehkonomiko-matematicheskikh metodov // Vestnik Voronezhskogo gosudarstvennogo agrarnogo universiteta. 2022. T. 15, № 2(73). S. 172–179. https//:doi.org/ 10.53914/issn2071-2243_2022_2_172–179.
5. Tryon R. C. Cluster Analysis; Correlation Profile and Orthometric (Factor) Analysis for the Isolation of Unities in Mind and Personality. – Ann Arbor, Mich.: Edwards brother, inc., lithoprinters and publishers. 1939.P.374.
6. Zhilov R.A. Primenenie neironnykh setei pri klasterizatsii dannykh // Izvestiya KBNTS RAN. 2021. №1 (99). URL: https://cyberleninka.ru/article/n/primenenie-neyronnyh-setey-pri-klasterizatsii-dannyh (data obrashcheniya: 26.06.2024).
7. Cheng J., Cline, M., Martin, J., Finkelstein, D., et al. Knowledge-Based Clustering Algorithm Driven by Gene Ontology // J. Biopharm Stat, 2004. No.14. P. 687–700.
8.Gichiev N. S. Klasternyi analiz v ehkonomike: teoreticheskii aspekt // RPPEH. 2020. №8 (118). URL: https://cyberleninka.ru/article/n/klasternyy-analiz-v-ekonomike-teoreticheskiy-aspekt (data obrashcheniya: 22.06.2024).
9.Prokhorenkov P.A., Reger T.V., Gudkova N.V. Metody klasternogo analiza v regional'nykh issledovaniyakh // Fundamental'nye issledovaniya. 2022. № 3. S. 100-106.
10. Dubrova T. A. Statisticheskie metody prognozirovaniya. M.: YUNITI, 2003. S. 178 – 184.
11. Klyuchnikov M.V. Klasternyi analiz krupneishikh bankov Rossii // Daidzhest-finansy. 2003. №2 (98). URL: https://cyberleninka.ru/article/n/klasternyy-analiz-krupneyshih-bankov-rossii (data obrashcheniya: 01.07.2024).
12. Kovalev V.E., Novikova K.V., Antineskul E.A. Klasternyi analiz prodovol'stvennykh riteilerov Rossii // Upravlenets. 2022. №2. URL: https://cyberleninka.ru/article/n/klasternyy-analiz-prodovolstvennyh-riteylerov-rossii (data obrashcheniya: 01.07.2024). 13. Shmatko A. D., Gubin S. V. Klasternyi analiz innovatsionnogo potentsiala sub"ektov RF // Upravlencheskoe konsul'tirovanie. 2020. №3 (135). URL: https://cyberleninka.ru/article/n/klasternyy-analiz-innovatsionnogo-potentsiala-subektov-rf (data obrashcheniya: 01.07.2024).