Segmentation of Manufacturing Enterprises by Operational–Financial Profiles Based on Digital Analysis of Corporate Data

Persistent operational-financial heterogeneity across manufacturing firms complicates peer benchmarking and digital investment program targeting. We segment Russian manufacturing enterprises using a reproducible pipeline that combines feature standardization, principal component analysis, k-means clustering, and panel-level label consolidation. The methodological framework integrates principal component analysis on standardized features and the k-means algorithm as tools of digital data analytics. The optimal number of clusters was determined by combining the elbow method, average silhouette, and Calinski–Harabasz and Davies–Bouldin indices. The cluster labels were consolidated across the observation horizon through modal membership, with tie-breaking based on the minimum average distance to the centroids. Five interpretable profiles were identified that differed in business scale, capital intensity, revenue and margin dynamics, leverage resilience, and liquidity. The final map contains five profiles (n = 6,479 firms): 45, 1,746, 993, 1,286, and 2,409 firms per cluster, differing in scale, capital intensity, profitability and turnover patterns, leverage tolerance, and liquidity. Across random restarts, agreement with the final partition is ARI  0.49 and NMI  0.43; the low mean silhouette is consistent with soft boundaries between adjacent profiles. To monitor managerial practices, we build a composite index from six indicators using intracluster min–max normalization and multi-year averaging, positioning each firm relative to its closest peers and highlighting reserves for productivity growth and faster capital turnover. Novelty lies in a fully reproducible segmentation workflow that integrates panel-level label consolidation and intracluster normalization for managerial benchmarking.

Clustering method; Digital transformation; Industrial data analytics; Manufacturing industry; Principal component analysis

Ahn, S., & Chang, S. (2019). A similarity-based hierarchical clustering method for manufacturing process models. Sustainability, 11(9), 2560. https://doi.org/10.3390/su11092560

Arruda, H. M., Bavaresco, R. S., Kunst, R., Bugs, E. F., Pesenti, G. C., & Barbosa, J. L. V. (2023). Data science methods and tools for Industry 4.0: A systematic literature review and taxonomy. Sensors, 23(11), 5010. https://doi.org/10.3390/s23115010

Blachowicz, T., Wylezek, J., Sokol, Z., & Bondel, M. (2025). Real-time analysis and classification of welding parameters using HDBSCAN and k-means clustering. Information, 16(2), 79. https://doi.org/10.3390/info16020079

Buggineni, V., Chen, C., & Camelio, J. (2024). Enhancing manufacturing operations with synthetic data: A systematic framework for data generation, accuracy, and utility. Frontiers in Manufacturing Technology, 4, 1320166. https://doi.org/10.3389/fmtec.2024.1320166

Chen, M.-K., Wu, S.-W., Huang, Y.-P., & Chang, F.-J. (2022). The key success factors for the operation of SME cluster business ecosystem. Sustainability, 14(14), 8236. https://doi.org/10.3390/su14148236

Chen, T., Sampath, V., May, M. C., Shan, S., Jorg, O. J., Aguilar Martín, J. J., & Calaon, M. (2023). Machine learning in manufacturing towards Industry 4.0. From “For Now” to “Four-Know”. Applied Sciences, 13(3), 1903. https://doi.org/10.3390/app13031903

Chen, X., Wang, E., Miao, C., Ji, L., & Pan, S. (2020). Industrial clusters as drivers of sustainable regional economic development. Sustainability, 12(7), 2848. https://doi.org/10.3390/su12072848

Chiang, T.-A., Che, Z.-H., Lee, C.-H., & Liang, W.-C. (2021). Applying clustering methods to develop an optimal storage-location planning-based consolidated picking methodology and operational sequencing. Applied Sciences, 11(21), 9895. https://doi.org/10.3390/app11219895

Cottineau, C., & Arcaute, E. (2020). The nested structure of urban business clusters. Applied Network Science, 5, 2. https://doi.org/10.1007/s41109-019-0246-9

Cui, Y., Niu, Y., Ren, Y., Zhang, S., & Zhao, L. (2024). A model to analyze industrial clusters to measure land use efficiency in China. Land, 13(7), 1070. https://doi.org/10.3390/land13071070

Dhondt, N., Mendez Alva, F., & Van Eetvelde, G. (2024). Introducing industrial clusters in multi-node energy system modelling for neutrality and security. Sustainability, 16(6), 2585. https://doi.org/10.3390/su16062585

Dmitriev, N., Zaytsev, A., Kichigin, O., & Yashchenko, E. (2022). Factor analysis of fixed capital investments: Regional aspect. TEM Journal, 11(3), 1108–1118. https://doi.org/10.18421/TEM113-16

Dmitriev, N. D., & Satmurzaev, M. M. (2025). The impact of corporate social responsibility on enhancing the intellectual potential of organizations. Economic Consultant, 3(49), 65–79. https://doi.org/10.46224/ecoc.2025.3.5

Eremina, I., & Rodionov, D. (2023). The special aspects of devising a methodology for predicting economic indicators in the context of situational response to digital transformation. International Journal of Technology, 14 (8), 1653–1662. https://doi.org/10.14716/ijtech.v14i8.6839

Faizullin, R. V., Ototsky, P. L., & Goriacheva, E. N. (2025). Assessing the impact of artificial intelligence on Russian labor market development scenarios: Industry analysis. Economic and Social Changes: Facts, Trends, Forecast, 18(1), 170–189. https://doi.org/10.15838/esc.2025.1.97.10

Gargalo, C. L., Malanca, A. A., Aouichaoui, A. R. N., Huusom, J. K., & Gernaey, K. V. (2024). Navigating Industry 4.0 and 5.0: The role of hybrid modelling in (bio)chemical engineering’s digital transition. Frontiers in Chemical Engineering, 6, 1494244. https://doi.org/10.3389/fceng.2024.1494244

Giordano, D., Mellia, M., & Cerquitelli, T. (2021a). A data-driven unsupervised multivariate segmentation and clustering method for anomaly detection in industrial contexts. Electronics, 10(10), 1166. https://doi.org/10.3390/electronics10101166

Giordano, L., Messina, F., Santoro, C., Scata, M., & Longo, F. (2021b). K-MDTSC. k-means-based multi-dimensional time series clustering for anomaly detection. Electronics, 10(14), 1728. https://doi.org/10.3390/electronics10141728

Glukhov, V., Shchepinin, V., Lyubek, Y., Babkin, I., & Karimov, D. (2023). Assessment of the impact of services and digitalization level on the infrastructure development in oil and gas regions. International Journal of Technology, 14(8), 1810–1820. https://doi.org/10.14716/ijtech.v14i8.6855

Herrero, Á. C., Sangüesa, J. A., Garrido, P., Martínez, F. J., & Calafate, C. T. (2023). Mo-BiSea: A mobility-based binary search to cluster product flows in e-commerce. Electronics, 12(15), 3262. https://doi.org/10.3390/electronics12153262

Hou, Z., Yan, R., & Wang, S. (2022). On the k-means clustering model for performance enhancement of port state control. Journal of Marine Science and Engineering, 10(11), 1608. https://doi.org/10.3390/jmse10111608

Hu, Q., Qi, H., Huang, W., & Liu, M. (2023). A method to recommend cloud manufacturing service based on spectral clustering and improved Slope One algorithm. Journal of Cloud Computing, 12, 115. https://doi.org/10.1186/s13677-023-00489-5

Ikotun, A. M., & Ezugwu, A. E. (2022). Boosting k-means clustering with symbiotic organisms search for automatic clustering problems. PLOS ONE, 17(8), e0272861. https://doi.org/10.1371/journal.pone.0272861

Kannan, R., Abdul Halim, H. A., Ramakrishnan, K., Ismail, S., & Wijaya, D. R. (2022). Machine learning approach for predicting production delays: A quarry company case study. Journal of Big Data, 9, 94. https://doi.org/10.1186/s40537-022-00644-w

Khan, A. A., & Abonyi, J. (2022). Simulation of sustainable manufacturing solutions. Tools for enabling circular economy. Sustainability, 14(15), 9796. https://doi.org/10.3390/su14159796

Kiliç, D. K., & Nielsen, P. (2022). Comparative analyses of unsupervised PCA k-means change detection algorithm from the viewpoint of follow-up plan. Sensors, 22(23), 9172. https://doi.org/10.3390/s22239172

Liu, H., & Ren, J. (2025). Intelligent manufacturing policy, ESG performance, and total factor productivity. PLOS ONE, 20(2), e0311369. https://doi.org/10.1371/journal.pone.0311369

Lu, Q., Wang, S., Jiang, M., Li, Y., & Dong, K. (2021). Main control factors and sensitivity analysis of an improved k-means clustering algorithm. PLOS ONE, 16(5), e0248840. https://doi.org/10.1371/journal.pone.0248840

Molinié, D., Madani, K., & Amarger, V. (2022). Clustering at the disposal of Industry 4.0. Automatic extraction of plant behaviors. Sensors, 22(8), 2939. https://doi.org/10.3390/s22082939

Mourtzis, D. (2022). Advances in adaptive scheduling in Industry 4.0. Frontiers in Manufacturing Technology, 2, 937889. https://doi.org/10.3389/fmtec.2022.937889

Pérez-Ortega, J., Almanza-Ortega, N. N., & Romero, D. (2018). Balancing effort and benefit of k-means clustering algorithms in big data realms. PLOS ONE, 13(9), e0201874. https://doi.org/10.1371/journal.pone.0201874

Pittino, F., Puggl, M., Moldaschl, T., & Hirschl, C. (2020). Automatic anomaly detection on in-production manufacturing machines using statistical learning methods. Sensors, 20(8), 2344. https://doi.org/10.3390/s20082344

Sandoyan, E., Rodionov, D., Voskanyan, M., & Galstyan, A. (2025). The role of digital technologies in capital market development: A pathway to economic growth in developing countries. International Journal of Technology, 16(2), 573–584. https://doi.org/10.14716/ijtech.v16i2.7421

Scharmer, V. M., Vernim, S., Horsthofer-Rauch, J., Jordan, P., Maier, M., Paul, M., & Zaeh, M. F. (2024). Sustainable manufacturing: A review and framework derivation. Sustainability, 16(1), 119. https://doi.org/10.3390/su16010119

Seo, D., Kim, S., Oh, S., & Kim, S.-H. (2022). K-means clustering-based safety system using wireless sensor networks in industrial sites. Sensors, 22(8), 2897. https://doi.org/10.3390/s22082897

Shirasawa, N., & Seo, Y. (2025). The role of institutional and geographic proximity in enhancing Creating Shared Value initiatives in an industrial cluster setting. Sustainability, 17(6), 2410. https://doi.org/10.3390/su17062410

Wang, T., Jing, Z., Zhang, S., & Qiu, C. (2023). Utilizing principal component analysis and hierarchical clustering to develop driving cycles. A case study in Zhenjiang. Sustainability, 15(6), 4845. https://doi.org/10.3390/su15064845

Wang, X., Xie, Z., Yan, F., Wang, J., Fan, J., Zeng, Z., Lu, J., Zhang, H., & Zeng, N. (2025). Towards more accurate industrial anomaly detection: A component-level feature-enhancement approach. Electronics, 14(8), 1613. https://doi.org/10.3390/electronics14081613

Yuan, C., & Yang, H. (2019). Research on K-value selection method of k-means clustering algorithm. J, 2(2), 226–235. https://doi.org/10.3390/j2020016

Zaytsev, A., & Dmitriev, N. (2025). Automated collection and processing of spatiotemporal data for the analysis of sustainable development in industrial systems. 2025 International Russian Smart Industry Conference (SmartIndustryCon), 1043–1050. https://doi.org/10.1109/SmartIndustryCon65166.2025.10986205

Zaytsev, A., Mihel, E., Dmitriev, N., Alferyev, D., & Laszlo, U. (2024). Optimization of interaction with counterparties: Selection game algorithm under uncertainty. Mathematics, 12, 2079. https://doi.org/10.3390/math12132079

Zhang, G., Li, Y., & Deng, X. (2020). K-means clustering-based electrical equipment identification for smart building application. Information, 11(1), 27. https://doi.org/10.3390/info11010027

Zhang, W., Bao, X., Hao, X., & Gen, M. (2025). Metaheuristics for multi-objective scheduling in smart manufacturing: A survey. Frontiers in Industrial Engineering, 3, 1540022. https://doi.org/10.3389/fie.2025.1540022

Zhao, C., Ma, C., & Zhang, H. (2022). Modeling manufacturing resources based on manufacturability features. Scientific Reports, 12, 10775. https://doi.org/10.1038/s41598-022-15072-2

Zhu, Y., Wang, R., Feng, M., Qin, L., Shia, B.-C., & Chen, M.-C. (2024). Supply chain analysis based on community detection of multi-layer weighted networks. Mathematics, 12(22), 3606. https://doi.org/10.3390/math12223606