Machine Learning in the Comprehensive Study of the Human Development Index

Introduction: An urgent task of regional policy consists not only in monitoring the human development index, but also in identifying key socio-economic factors determining its level. Realizing these dependencies necessitates the development of evidence-based measures to reduce inter-regional inequality and improve the quality of life.

Methods: The study is based on the analysis of official statistical data. The target indicator was transformed into a binary variable for classification tasks based on the median value. After processing the gaps and generating new features, six machine learning algorithms, including linear and ensemble methods, were trained and optimized. A stacking ensemble was additionally developed to integrate their strengths. The quality of the models was assessed using complex metrics in a test sample.

Results: Correlation analysis has revealed a strong negative relationship between the index and the level of poverty and unemployment, and a strong positive relationship with the indicators of demographic burden and economic activity. Among the models, gradient boosting demonstrated the best predictive ability, reaching an accuracy of 0.8824 and a ROC-AUC value of 0.9523. The stacking ensemble has enabled us to obtain a balanced classifier with competitive indicators.

Discussion: The results have confi rmed the effectiveness of modern ensemble methods for modeling complex socio-economic dependencies. The constructed models serve as a tool for analytical support of management decisions, providing the opportunity to assess the potential impact of changes in individual areas on the integral indicator of the region’s development. The future work will focus on providing a more profound interpretation of the models to develop specifi c recommendations.

1. Astapov, R. L., Mukhamadeeva, R. M. (2021) Selection’s Automatization of Machine Learning Parameters and Training a Machine Learning Model. Current scientifi c research in the modern world. No. 5-2 (73). P. 34–37. EDN: GJEUNW (In Russ.)

2. Butsenko, I. N. (2024) Human Development Index — a tool for comparing global trends in human development. Current problems and prospects for economic development: Proceedings of the XXIII International Scientifi c and Practical Conference, Simferopol – Gurzuf, October 17–19, 2024. Simferopol: IP Zueva T. V. Pp. 72–74. EDN: HOCTKY (In Russ.)

3. Kamaldinova, I. M., Mukhametshina, G. R. (2023) Analysis of Russian Human Development Index and Its Role in The Pace of Economic Development of Country. Bulletin of the Rostov State Economic University (RINH). Vol. 28, no. 2. Pp. 106–114. DOI: 10.54220/v.rsue.1991-0533.2023.2.28.013. EDN: AYMPQE (In Russ.)

4. Kameneva, A. I., Karpukhno, I. A. (2019) Dependence of the Human Development Index on the Growth of Gross Domestic Product: The Case of Norway. Economic Theory in the Context of Economic Globalization: Abstracts of Reports and Presentations at the XI International Scientifi c and Practical Conference of Students and Young Scientists. Donetsk, March 13–14, 2019 / General Editor L. I. Dmitrichenko. Donetsk: Donetsk National University. Pp. 172–173. EDN: NGLVAN (In Russ.)

5. Kolosov, V. S. (2025) Possibilities of Hyperparameter Optimization for Developing Gradient Boosting Models: The Case of an Open Dataset. Medicine of the Future 2025: Proceedings of the All-Russian Scientifi c Forum with International Participation. Tyumen, March 27–29, 2025. Tyumen: RIC “Aivex”. Pp. 149–150. EDN: FSBJOT (In Russ.)

6. Kuznetsova, M. V., Ivashina, N. S. (2019) Socio-economic development through the prism of human development indices and human capital development. Sustainable development of territories: theory and practice: Proceedings of the 10th All-Russian scientifi c and practical conference with international participation. In 2 vol. Sibay, November 14–16, 2019. Vol. 2. Sibay: Sibay Information Center-branch of the State Unitary Enterprise of the Republic of Bashkortostan Publishing House. Pp. 357–359. EDN: EUUTNA (In Russ.)

7. Makarov, S. M. (2025) Forecasting the Level of Deviations in the Production Process Using Regression Based on Gradient Boosting. Paradigm. No. 5-2. Pp. 137–144. EDN: IFPBFR (In Russ.)

8. Mikhailova, S. S., Grineva, N. V. (2024) Development of a Binary Classifi cation Model Based on Small Data Using Machine Learning Methods. Economics Problems and Legal Practice. Vol. 20, no. 1. Pp. 129–140. DOI: 10.33693/2541-8025-2024-20-1-129-140. EDN: WFJKOK (In Russ.)

9. Rukomin, M. A. (2025) Review of Ensemble Models in Predictive Analytics and Their Comparison with Traditional Machine Learning Approaches. Vestnik nauki. Vol. 1, no. 8 (89). Pp. 368–373. EDN: GJBKYS (In Russ.)

10. Shutkina, E. V., Kurashkin, S. O. (2024) Application of the CATBOOST Method to the Problem of Predicting CCHD Prediction. Actual Problems of Aviation and Cosmonautics: Collection of Materials of the X International Scientifi c and Practical Conference Dedicated to the 100th Anniversary of Academician M. F. Reshetnev and Cosmonautics Day: in 3 vol. Krasnoyarsk, April 8–12, 2024. Krasnoyarsk: Siberian State University of Science and Technology named after academician M. F. Reshetnev. Pp. 251–253. EDN: LDGCVK (In Russ.)