Journal of Siberian Federal University. Humanities & Social Sciences / Machine Learning-Based Regional Clustering to Guide State Support for the Agro- Industrial Complex

Full text (.pdf)
Issue
Journal of Siberian Federal University. Humanities & Social Sciences. 2026 19 (6)
Authors
Semenova, Anna R.; Cherkasova, Yuliya I.
Contact information
Semenova, Anna R. : Siberian Federal University (Krasnoyarsk, Russian Federation); Cherkasova, Yuliya I. : Siberian Federal University (Krasnoyarsk, Russian Federation);
Keywords
CatBoost; K-Means; RandomForestClassifier; subsidies; machine learning; clustering; classification; agricultural sector; CatBoost; K-Means; RandomForestClassifier; confusion matrix
Abstract

The article proposes using machine learning methods for clustering the agricultural sector to provide state financial support. Based on crop production data from 82 constituent entities of the Russian Federation for 2024, clustering and classification of Russian regions were performed using the K-Means and RandomForestClassifier algorithms. To predict the volume of agricultural output, a CatBoost model with preliminary feature engineering was used. It is shown that the regions are clearly divided into four clusters: super-leaders, leaders, middle, and lagging. The classification model demonstrates high predictive ability (accuracy = 0.9048). The obtained results provide a rationale for differentiated state support measures for the agricultural sector

Pages
1293–1305
EDN
XAZZVH
Paper at repository of SibFU
https://elib.sfu-kras.ru/handle/2311/158610

Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).