Abstract :

Foreign direct investment (FDI) is an important factor in the economic development of Central Asian countries, where investment flows have traditionally been concentrated in resource-based sectors. In the context of a growing focus on diversification, the need to analyze and study the determinants of FDI is increasing.

This study examines the determinants of FDI inflows in Central Asian countries using machine learning methods (CatBoost) and explainable artificial intelligence (SHAP), and compares the results with a classical econometric approach based on a two-way fixed effects (TWFE) model. Given the limited availability of data, a transfer learning approach is applied: the model is first trained on a group of countries structurally similar to Central Asia and then fine-tuned on the regional sample.

The results show that key macroeconomic factors such as Trade (% of GDP), Current account balance (% of GDP), and several other macroeconomic variables remain significant across both methodologies. At the same time, ML identifies additional regional patterns, such as a higher importance for FDI of determinants including Adjusted savings: carbon dioxide damage (% of GNI), Urban population (% of total population), and Access to electricity (% of population), among others.

The findings indicate that XAI provides interpretable results that are consistent with classical methods and additionally allows for capturing nonlinearities and regional heterogeneity. The study extends the application of ML and XAI in data-constrained Central Asian settings and demonstrates the value of combining econometric and machine learning approaches in the analysis of FDI determinants.

---

Keywords :

CatBoost, Central Asia, Explainable Artificial Intelligence (XAI), Foreign Direct Investment (FDI), Investment Determinants, Machine learning, SHAP

---

References :

1. Kumari, J. (2014). Foreign Direct Investment and Economic Growth: A Literature Survey.
2. Udeh, E., Ibrahim, D., & Sesay, B. (2025). The Relationship between Foreign Direct Investment and Economic Growth: A Review of the Literature (1994-2023). International Journal of Science and Management Studies (IJSMS).
3. Kehal, H. (2004). Foreign investment in developing countries.
4. Singh, D., & Turała, M. (2022). Machine Learning and Regularization Technique to Determine Foreign Direct Investment in Hungarian Counties. DANUBE, 13, 269 – 291.
5. Singh, D. (2023). Comparison between artificial neural network and linear model prediction performance for FDI disparity and the growth rate of companies in Hungarian counties. Int. J. Bus. Inf. Syst., 43, 542-552.
6. Singh, D. (2021). Interpretable Machine-Learning Approach in Estimating FDI Inflow: Visualization of ML Models with LIME and H2O. TalTech Journal of European Studies, 11, 133 – 152.
7. Singh, D. (2023). Foreign direct investment and local interpretable model-agnostic explanations: a rational framework for FDI decision making. Journal of Economics, Finance and Administrative Science.
8. Alon, I., Bretas, V.P., Sclip, A., & Paltrinieri, A. (2022). Greenfield FDI attractiveness index: a machine learning approach. Competitiveness Review: An International Business Journal.
9. Kemives, A., Randelovic, M., Barjaktarović, L., Dikanovic, P., Čabarkapa, M.D., & Randelovic, D.M. (2024). Identifying Key Indicators for Successful Foreign Direct Investment through Asymmetric Optimization Using Machine Learning. Symmetry, 16, 1346.
10. Prince, W., & Fantom, N.J. (2014). World development indicators 2014 : highlights.
11. Woodbridge, J.M. (2002). Econometric Analysis of Cross Section and Panel Data.
12. Pan, S.J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22, 1345-1359.
13. Friedman, J.H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29, 1189-1232.
14. Shao, Z., & Er, M.J. (2016). Efficient Leave-One-Out Cross-Validation-based Regularized Extreme Learning Machine. Neurocomputing, 194, 260-270.
15. Shapley, L.S. (1988). A Value for n-person Games.
16. Lundberg, S.M., & Lee, S. (2017). A Unified Approach to Interpreting Model Predictions. Neural Information Processing Systems.