NALYSIS OF METHODS FOR FORECASTING SOCIO-ECONOMIC VULNERABILITIES OF COUNTRIES
Abstract
This study presents a bibliometric analysis of publications focused on the methods of forecasting socio-economic vulnerabilities of countries using Scopus database and visualised with VOSviewer tools. Covering 1991–2025, it shows slow early growth and rapid expansion after 2015, reflecting rising academic interest driven by global challenges, including economic crises, inequality, and illicit practices. Leading contributors are China, the US, and India, while European and other countries show moderate activity, indicating potential for further research. The field is interdisciplinary, with most works in Business, Management and Accounting, and Economics, Econometrics and Finance, alongside contributions from Computer Science, Engineering, Decision Sciences, Social Sciences, and Environmental Science. Bibliometric clustering identifies seven research directions: AI and NLP for vulnerability assessment and cybersecurity; machine learning in socio-economic and environmental systems; statistical and probabilistic modelling for risk management and disaster prevention; algorithmic optimization and software analysis; trajectory modelling in autonomous systems; probabilistic financial forecasting; and public finance, budgeting, and early warning systems. The study emphasizes the growing role of modern analytical tools – machine learning, deep neural networks, and Bayesian modelling – for improving prediction accuracy and supporting decision-making. Future research should integrate cyber threats, corruption, and money laundering into forecasting models. Recurrent neural networks, particularly GRU, are promising for modelling temporal dynamics and capturing short-term fluctuations and long-term trends in socio-economic vulnerability, enhancing prediction reliability and enabling proactive strategies for risk mitigation and economic resilience. The findings contribute to understanding methodological approaches, emerging trends, and research gaps, offering insights for academic research and practical socio-economic risk management.
References
Balcaen S., & Ooghe H. (2006) 35 years of studies on business failure: an overview of the classic statistical methodologies and their related problems. The British Accounting Review, vol. 38(1), pp. 63-93. DOI: 10.1016/j.bar.2005.09.001
Swain S. S., Rao R. R., Reddy C. R. M., Kaur H., & Boopathi S. (2025) Predictive Analytics for Urban Development Using ML Technique. In Urban Mobility and Challenges of Intelligent Transportation Systems (pp. 383-402). IGI Global Scientific Publishing. DOI: 10.4018/979-8-3693-7984-4.ch021
Zhao J., Shao M., Wang H., Yu X., Li B., & Liu X. (2022) Cyber threat prediction using dynamic heterogeneous graph learning. Knowledge-Based Systems, vol. 240, no. 108086. DOI: 10.1016/j.knosys.2021.108086
Rajesh R., Agariya A. K., & Rajendran C. (2021) Predicting resilience in retailing using grey theory and moving probability based Markov models. Journal of Retailing and Consumer Services, vol. 62, no. 102599. DOI: 10.1016/j.jretconser.2021.102599
Sethi P., Singh A., & Gupta V. (2025) Predicting Financial Distress Using Machine Learning Techniques. Asia-Pacific Financial Markets, 1-23. DOI: 10.1007/s10690-025-09525-7
Sharma V., Vashishth T. K., Sharma K. K., Kaushik V., Sharma M. K., & Sharma R. (2026) Financial Forecasting and Cybersecurity with Convolutional Neural Networks: Trends and Challenges. AI-Powered Cybersecurity for Banking and Finance, 204-239. DOI: 10.4324/9781003596875-10
Zhao J., Su X., Li X., Xi X., & Yao X. (2025) Forecasting technology convergence with the spatiotemporal link prediction model. Technovation, vol. 146, no. 103289. DOI: 10.1016/j.technovation.2025.103289
Sun X., Yuan P., Yao F., Qin Z., Yang S., & Wang X. (2025) Financial fragility in emerging markets: Examining the innovative applications of machine learning design methods. Journal of the Knowledge Economy, vol. 16(2), pp. 5862-5883. DOI: 10.1007/s13132-023-01731-w
Koc K. (2023) Role of national conditions in occupational fatal accidents in the construction industry using interpretable machine learning approach. Journal of Management in Engineering, vol. 39(6), no. 04023037. DOI: 10.1061/JMENEA.MEENG-5516
Manousiadis C., & Gaki E. (2023) Prediction models and testing of resilience in regions: Covid19 economic impact in USA counties study case. REGION, vol. 10(1), pp. 113-132. DOI: 10.18335/region.v10i1.449
VOSviewer. Visualizing scientific landscapes. URL: https://www.vosviewer.com (accessed December 10, 2025)
This work is licensed under a Creative Commons Attribution 4.0 International License.
