THE USE OF ARTIFICIAL INTELLIGENCE IN FORECASTING FOREIGN TRADE FLOWS
Abstract
In the context of global economic uncertainty and rapidly changing trade dynamics, the application of artificial intelligence in forecasting foreign trade flows has become increasingly relevant and strategically important. The article examines the use of artificial intelligence technologies in forecasting foreign trade flows, emphasizing their growing significance for enhancing the accuracy, speed, and reliability of decision-making in international economic management. The study analyzes modern approaches based on machine learning and deep learning algorithms that enable the identification of complex nonlinear relationships between macroeconomic indicators, trade volumes, currency fluctuations, and geopolitical factors. It outlines the main stages of building AI-driven forecasting systems, including data collection, preprocessing, model training, evaluation, and visualization of predictive outcomes. The advantages of neural networks, ensemble methods, and predictive analytics over traditional econometric techniques are demonstrated through comparative analysis using key evaluation metrics such as MAE, RMSE, and MAPE. The findings reveal that artificial intelligence significantly improves forecasting precision and adaptability in dynamic global environments, reducing analytical time and facilitating proactive management of international trade processes. The research also discusses existing challenges – data quality, implementation costs, interpretability, and ethical aspects – and suggests practical recommendations to overcome these barriers through standardization, cross-agency data integration, and the development of explainable AI tools. The results can be applied to improve analytical systems supporting export-import policy planning, enhance risk management, and create integrated digital platforms for real-time monitoring of global trade flows. Future research should focus on hybrid modeling approaches that combine traditional econometrics, machine learning, and big data analytics to ensure the transparency, sustainability, and long-term efficiency of international trade forecasting systems.
References
Han, X., Lin, T. X., & Wang, X. Mitigate cross-market competition caused by the risk of uncertainty and improve firm performance through business intelligence. Heliyon, 2024. No. 10(14). DOI: https://doi.org/10.1016/j.heliyon.2024.e34542
Mensah, G. K., & Gottwald, W. D. Enterprise risk management: Factors associated with effective implementation. Risk Governance and Control: Financial Markets & Institutions, 2016. No. 6(4). DOI: https://doi.org/10.22495/rcgv6i4c1art9
Slassi-sennou S., Elmouhib S. Managing Financial and Operational Risks Through Digital Transformation: The Mediating Influence of Information and Communication Technologies’ Adoption and Resistance to Change. Journal of Risk and Financial Management, 2025. No. 18(3):128. DOI: https://doi.org/10.3390/jrfm18030128
Franco, M., Minatogawa, V., & Quadros, R. How Transformative Business Model Renewal Leads to Sustained Exploratory Business Model Innovation in Incumbents: Insights from a System Dynamics Analysis of Case Studies. Systems, 2023. No. 11(2). DOI: https://doi.org/10.3390/systems11020060
Bashynska I., Prokopenko O. Mitigating Cyber Risks in AI-Driven Circular Economy Implementations. Scientific Journal of Bielsko-Biala School of Finance and Law, 2024. No. 28(4), pp. 65–71. DOI: https://doi.org/10.19192/wsfip.sj4.2024.10
Feng, R. What are risk sciences? Risk Sciences, 2025. no. 1. DOI: https://doi.org/10.1016/j.risk.2025.100029
Filyppova S., Bashynska I., Kholod B., Prodanova L., Ivanchenkova L., Ivanchenkov V. Risk management through systematization: Risk Management Culture. International Journal of Recent Technology and Engineering, 2019. No. 8(3), pp. 6047–6052. DOI: https://doi.org/10.35940/ijrte.C5601.098319
Hanay, U., İnce, H., & Işık, G. Identifying Key Factors of Reputational Risk in Finance Sector Using a Linguistic Fuzzy Modeling Approach. Systems, 2024. No. 12(10). DOI: https://doi.org/10.3390/systems12100440
Chotia, V., Khoualdi, K., Broccardo, L., & Yaqub, M. Z. The role of cyber security and digital transformation in gaining competitive advantage through Strategic Management Accounting. Technology in Society, 2025. No. 81, DOI: https://doi.org/10.1016/j.techsoc.2025.102851
Malynovska Y., Bashynska I., Cichoń D., Malynovskyy Y., Sala D. Enhancing the Activity of Employees of the Communication Department of an Energy Sector Company. Energies. 2022. No. 15(13). DOI: https://doi.org/10.3390/en15134701
Huang, H. Technology-Driven Financial Risk Management: Exploring the Benefits of Machine Learning for Non-Profit Organizations. Systems, 2024. No. 12(10). DOI: https://doi.org/10.3390/systems12100416
