Discrimination of Individual Russian Regions in Socio-Economic Clustering Based on the Kohonen Neural Network
DOI:
https://doi.org/10.52575/2687-0932-2025-52-1-5-18Keywords:
regional socio-economic development, cluster analysis, Kohonen self-organizing maps, spatial algorithmic bias, discriminated region, fair clustering, Russian FederationAbstract
The article is devoted to the detection of algorithmic bias in the results of Russian regions’ socio-economic clustering based on the Kohonen neural network which have been published in scientific journals. The study reveals potentially biased operations in self-organizing maps. Sixty-five articles on neural network and 604 articles on traditional socio-economic clustering of regions have been found. The author proposes that the arrays of articles on neural network and traditional clustering should be divided into three bodies of publications: those devoted to all Russian regions, the ones focused on regions of the same federal district, and the papers describing a sample of regions. The main conclusions are drawn for the corpus of articles that is focused on all regions. As a result of comparing biased operations with the domestic experience of socio-economic clustering of regions, three types of spatial algorithmic bias were found in self-organizing maps. These may be conditionally described as regional segregation (exclusion of a region from clustering), cluster compression (limitation of the number of clusters) and range bias (transformation of cluster size). It is shown that, compared with traditional clustering, the use of a neural network algorithm leads to the formation of clusters with as many regions as possible. The author provides lists of potentially discriminated regions for two existing cluster solutions and presents five areas of further research. The practical significance is associated with the discovery of shortcomings in the existing methodology for constructing an algorithm for fair neural network clustering of Russian regions based on socio-economic data.
Acknowledgements: the study was carried out at the expense of the state task (topic registration No. AAAA21-121012190018-2).
Downloads
References
Список литературы
Блануца В.И. 2020. Региональные экономические исследования с использованием алгоритмов искусственного интеллекта: состояние и перспективы. Вестник Забайкальского государственного университета, 26 (8): 100–111.
Блануца В.И. 2022. Кластеризация регионов Сибири и Дальнего Востока по достижению национальных целей развития. Российский экономический журнал, 3: 63–83.
Блануца В.И. 2024. Пространственная алгоритмическая предвзятость в социально-экономической кластеризации российских регионов. Пространственная экономика, 20 (2): 71–92.
Гагарина Г.Ю., Дзюба Е.И., Губарев Р.В., Файзуллин Ф.С. 2017. Прогнозирование социально-экономического развития российских регионов. Экономика региона, 13 (4): 1080–1094.
Игнатьева А.Е., Серкова Е.Д., Мариев О.С. 2015. Сравнительные преимущества российских регионов в развитии и размещении производительных сил. Вестник Челябинского государственного университета, 18: 98–104.
Летягина Е.Н., Перова В.И. 2021. Нейросетевое моделирование региональных инновационных экосистем. Journal of New Economy, 22 (1): 71–89.
Перова В.И., Папко А.В. 2019. Нейросетевой анализ динамики инвестиционной деятельности регионов Российской Федерации. Вестник Нижегородского университета им. Н.И. Лобачевского. Серия: Социальные науки, 1: 24–32.
Серкова А.Е., Игнатьева Е.Д., Мариев О.С. 2014. Оценка социально-экономического развития российских регионов-субъектов Российской Федерации. Вестник Челябинского государственного университета, 21: 112–120.
Трифонов Ю.В., Сочков А.Л., Соловьёв А.Е. 2021. Оценка экономического потенциала регионов РФ на основе методологии нейросетевого кластерного анализа. Вестник Нижегородского университета им. Н.И. Лобачевского. Серия: Социальные науки, 3: 38–47.
Чередниченко Л.Г., Губарев Р.В., Дзюба Е.И., Файзуллин Ф.С. 2020. Целевое управление инновационным развитием России. Вестник СПбГУ. Экономика, 36 (2): 319–350.
Agarwal P., Skupin A. (Eds.) 2008. Self-Organising Maps: Applications in Geographic Information Science. Chichester; Hoboken: Wiley, 214 p.
Carboni O., Russu P. 2015. Assessing regional wellbeing in Italy: An application of Malmquist DEA and self-organizing map neural clustering. Social Indicators Research, 122 (3): 677–700.
Chabra A., Masalkovaitй K., Mohapatra P. 2021. An overview of fairness in clustering. IEEE Access, 9: 130698–130720.
Charrad M., Ghazzali N., Boiteau V., Niknafs A. 2014. NbClust: An R package for determining the relevant number of clusters in a data set. Journal of Statistical Software, 61 (6): 1–36.
Favaretto M., De Clercq B.S. 2019. Big data and discrimination: Perils, promises and solutions. A systematic review. Journal of Big Data, 6 (1): 12–27.
Giordani P., Ferraro M.B., Martella F. 2020. An Introduction to Clustering with R. Singapore: Springer, 340 p.
Gupta S., Ghalme G., Krishnan N.C., Jain S. 2023. Efficient algorithms for fair clustering with a new notion of fairness. Data Mining and Knowledge Discovery, 37: 1959–1997.
Hadi A.S. 2022. A new distance between multivariate clusters of varying locations, elliptical shapes, and directions. Pattern Recognition, 129: 108780.
Jackson M.C. 2021. Artificial intelligence and algorithmic bias: The issues with technology reflecting history and humans. Journal of Business and Technology Law, 16 (2): 299–316.
Khanchouch I., Charrad M., Limam M. 2015. A comparative study of multi-SOM algorithms for determining the optimal number of clusters. International Journal of Future Computer and Communication, 4 (3): 198–202.
Khasanah A.U. 2016. A comparison study: Clustering using self-organizing map and k-means algorithm. Performa, 15 (1): 51–58.
Kohonen T. 1982. Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43: 59–69.
Kohonen T. 2001. Self-Organizing Maps. Third Edition. Berlin; Heidelberg: Springer, 502 p.
Kordzadeh N., Ghasemaghaei M. 2022. Algorithmic bias: Review, synthesis, and future research directions. European Journal of Information Systems, 31 (3): 388–409.
Kourtit K., Arribas-Bel D., Nijkamp P. 2012. High performance in complex spatial systems: A self-organizing mapping approach with reference to The Netherlands. The Annals of Regional Science, 48: 501–527.
Lуpez-Villuendas A.M., del Campo C. 2023. Regional economic disparities in Europe: Time-series clustering of NUTS 3 regions. International Regional Science Review, 46 (3): 265–298.
Lorimer T., Held J., Stoop R. 2017. Clustering: How much bias do we need? Philosophical Transactions of the Royal Society A, 375: 20160293.
Mirkin B. 1996. Mathematical Classification and Clustering. Dordrecht; Boston; London: Kluwer Academic Publisher, 429 p.
Nishant R., Schneckenberg D., Ravishankar M. The formal rationality of artificial intelligence-based algorithms and the problem of bias. Journal of Information Technology, 39 (1): 19–40.
Robinson C., Franklin R.S. 2020. The sensor desert quandary: What does it mean (not) to count in the smart city? Transactions of the Institute of British Geographers, 46 (2): 238–254.
Ros F., Riad R., Guillaume S. 2024. Deep clustering framework review using multicriteria evaluation. Knowledge-Based Systems, 285: 111315.
Schmidt C.R., Rey S.J., Skupin A. 2011. Effects of irregular topology in spherical self-organizing maps. International Regional Science Review, 34 (2): 215–229.
Soares J.O., Coutinho C.C. 2010. Cluster analysis in regional science. Advances and Applications in Statistical Science, 1 (2): 311–325.
Van Giffen B., Herhausen D., Fahse T. 2022. Overcoming the pitfalls and perils of algorithms: A classification of machine learning biases and mitigation methods. Journal of Business Research, 144: 93–106.
Wei X., Zhang Z., Huang H., Zhou Y. 2024. An overview on deep clustering. Neurocomputing, 590: 127761.
Yin H. 2008. The self-organizing maps: Background, theories, extensions and applications. In: Fulcher J., Jain L.C. (Eds.). Computational Intelligence: A Compendium. Berlin: Springer, 715–762.
References
Blanutsa V.I. 2020. Regional economic research using artificial intelligence algorithms: state and prospects. Bulletin of Zabaikalsky State University, 26 (8): 100–111 (in Russian).
Blanutsa V.I. 2022. Clustering the regions of Siberia and the Far East to achieve national development goals. Russian Economic Journal, 3: 63–83 (in Russian).
Blanutsa V.I. 2024. Spatial algorithmic bias in socio-economic clustering of Russian regions. Spatial Economics, 20 (2): 71–92 (in Russian).
Gagarina G.Yu., Dzyuba E.I., Gubarev R.V., Fayzullin F.S. 2017. Forecasting the socio-economic development of Russian regions. Economics of the Region, 13 (4): 1080–1094 (in Russian).
Ignatieva A.E., Serkova E.D., Mariev O.S. 2015. Comparative advantages of Russian regions in the development and location of productive forces. Bulletin of the Chelyabinsk State University, 18: 98–104 (in Russian).
Letyagina E.N., Perova V.I. 2021. Neural network modeling of regional innovation ecosystems. Journal of New Economy, 22 (1): 71–89 (in Russian).
Perova V.I., Papko A.V. 2019. Neural network analysis of the dynamics of investment activity in the regions of the Russian Federation. Bulletin of the Nizhny Novgorod Lobachevsky University. Series: Social Sciences, 1: 24–32 (in Russian).
Serkova A.E., Ignatieva E.D., Mariev O.S. 2014. Assessment of socio-economic development of Russian regions-subjects of the Russian Federation. Bulletin of the Chelyabinsk State University, 21: 112–120 (in Russian).
Trifonov Yu.V., Sochkov A.L., Solovyov A.E. 2021. Assessment of the economic potential for the Russian Federation’s regions based on the methodology of neural network cluster analysis. Bulletin of the Nizhny Novgorod Lobachevsky University. Series: Social Sciences, 3: 38–47 (in Russian).
Cherednichenko L.G., Gubarev R.V., Dzyuba E.I., Fayzullin F.S. 2020. Targeted management of Russia's innovative development. Bulletin of St. Petersburg State University. Economics, 36 (2): 319–350 (in Russian).
Agarwal P., Skupin A. (Eds.) 2008. Self-Organising Maps: Applications in Geographic Information Science. Chichester; Hoboken: Wiley, 214 p.
Carboni O., Russu P. 2015. Assessing regional wellbeing in Italy: An application of Malmquist DEA and self-organizing map neural clustering. Social Indicators Research, 122 (3): 677–700.
Chabra A., Masalkovaitй K., Mohapatra P. 2021. An overview of fairness in clustering. IEEE Access, 9: 130698–130720.
Charrad M., Ghazzali N., Boiteau V., Niknafs A. 2014. NbClust: An R package for determining the relevant number of clusters in a data set. Journal of Statistical Software, 61 (6): 1–36.
Favaretto M., De Clercq B.S. 2019. Big data and discrimination: Perils, promises and solutions. A systematic review. Journal of Big Data, 6 (1): 12–27.
Giordani P., Ferraro M.B., Martella F. 2020. An Introduction to Clustering with R. Singapore: Springer, 340 p.
Gupta S., Ghalme G., Krishnan N.C., Jain S. 2023. Efficient algorithms for fair clustering with a new notion of fairness. Data Mining and Knowledge Discovery, 37: 1959–1997.
Hadi A.S. 2022. A new distance between multivariate clusters of varying locations, elliptical shapes, and directions. Pattern Recognition, 129: 108780.
Jackson M.C. 2021. Artificial intelligence and algorithmic bias: The issues with technology reflecting history and humans. Journal of Business and Technology Law, 16 (2): 299–316.
Khanchouch I., Charrad M., Limam M. 2015. A comparative study of multi-SOM algorithms for determining the optimal number of clusters. International Journal of Future Computer and Communication, 4 (3): 198–202.
Khasanah A.U. 2016. A comparison study: Clustering using self-organizing map and k-means algorithm. Performa, 15 (1): 51–58.
Kohonen T. 1982. Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43: 59–69.
Kohonen T. 2001. Self-Organizing Maps. Third Edition. Berlin; Heidelberg: Springer, 502 p.
Kordzadeh N., Ghasemaghaei M. 2022. Algorithmic bias: Review, synthesis, and future research directions. European Journal of Information Systems, 31 (3): 388–409.
Kourtit K., Arribas-Bel D., Nijkamp P. 2012. High performance in complex spatial systems: A self-organizing mapping approach with reference to The Netherlands. The Annals of Regional Science, 48: 501–527.
Lуpez-Villuendas A.M., del Campo C. 2023. Regional economic disparities in Europe: Time-series clustering of NUTS 3 regions. International Regional Science Review, 46 (3): 265–298.
Lorimer T., Held J., Stoop R. 2017. Clustering: How much bias do we need? Philosophical Transactions of the Royal Society A, 375: 20160293.
Mirkin B. 1996. Mathematical Classification and Clustering. Dordrecht; Boston; London: Kluwer Academic Publisher, 429 p.
Nishant R., Schneckenberg D., Ravishankar M. The formal rationality of artificial intelligence-based algorithms and the problem of bias. Journal of Information Technology, 39 (1): 19–40.
Robinson C., Franklin R.S. 2020. The sensor desert quandary: What does it mean (not) to count in the smart city? Transactions of the Institute of British Geographers, 46 (2): 238–254.
Ros F., Riad R., Guillaume S. 2024. Deep clustering framework review using multicriteria evaluation. Knowledge-Based Systems, 285: 111315.
Schmidt C.R., Rey S.J., Skupin A. 2011. Effects of irregular topology in spherical self-organizing maps. International Regional Science Review, 34 (2): 215–229.
Soares J.O., Coutinho C.C. 2010. Cluster analysis in regional science. Advances and Applications in Statistical Science, 1 (2): 311–325.
Van Giffen B., Herhausen D., Fahse T. 2022. Overcoming the pitfalls and perils of algorithms: A classification of machine learning biases and mitigation methods. Journal of Business Research, 144: 93–106.
Wei X., Zhang Z., Huang H., Zhou Y. 2024. An overview on deep clustering. Neurocomputing, 590: 127761.
Yin H. 2008. The self-organizing maps: Background, theories, extensions and applications. In: Fulcher J., Jain L.C. (Eds.). Computational Intelligence: A Compendium. Berlin: Springer, 715–762.
Abstract views: 49
Share
Published
How to Cite
Issue
Section
Copyright (c) 2025 Economics. Information Technologies
This work is licensed under a Creative Commons Attribution 4.0 International License.
