Global Journal of Economic and Finance Research

This research aims to evaluate and compare the effectiveness of various machine learning models in predicting sovereign debt and currency crises across different regions. By applying several machine learning algorithms, the study assesses these models' performance using accuracy and Root Mean Square Error (RMSE) metrics. The scope includes global, Africa and Middle East, Asia, Latin America, and Europe regions, with a particular focus on the impact of region-specific economic conditions and data quality. The methodology involves training and validating these models on historical financial data, followed by a comparative analysis of their predictive capabilities. The findings reveal that Gaussian Naive Bayes consistently outperforms other models in terms of accuracy and RMSE, especially in global and European contexts. KNN and Neural Networks also demonstrate strong performance. The conclusions emphasize the robustness of Gaussian Naive Bayes and the importance of tailoring predictive models to regional characteristics. Practical implications include recommendations for investors, financial managers, government agencies, and policymakers on adopting advanced machine learning techniques for improved crisis prediction and management. The study's original contribution lies in its comprehensive evaluation of machine learning models and the integration of behavioral finance, financial instability, modern portfolio, and information asymmetry theories to enhance predictive accuracy and reliability.

Financial Crisis Prediction, Machine Learning, Economic Stability

1. Akerlof, G. A. (1970). The market for “lemons”: Quality uncertainty and the market mechanism. The Quarterly Journal of Economics, 84(3), 488-500.
2. Agarwal, R. Improving Accuracy of Classification Based on C4.5 Decision Tree Algorithm Using Big Data Analytics. Computational Intelligence in Data Mining. Adv. Intell. Syst. Comput. 2019, 711, 203–211.
3. Arazmuradov, A. Assessing sovereign debt default by efficiency. J. Econ. Asymmetries 2016, 13, 100–113.
4. Ari, A.; Cergibozan, R. The Twin Crises: Determinants of Banking and Currency Crises in the Turkish Economy. Emerg. Mark. Financ. Trade 2016, 52, 123–135.
5. Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32.
6. Billio, M.; Casarin, R.; Costola, M.; Pasqualini, A. An entropy-based early warning indicator for systemic risk. J. Int. Financ. Mark. Inst. Money 2016, 45, 42–59.
7. Boonman, T.M.; Jacobs, J.P.A.M.; Kuper, G.H.; Romero, A. Early Warning Systems for Currency Crises with Real-Time Data. Open Econ. Rev. 2019, 30, 813–835.
8. Boonman, T.M.; Jacobs, J.P.A.M.; Kuper, G.H. Sovereign Debt Crises in Latin America: A Market Pressure Approach. Emerg. Mark. Financ. Trade 2015, 51, S80–S93. 
9. Boonman, T.M.; Urbina, A.E.S. Extreme Bounds Analysis in Early Warning Systems for Currency Crises. Open Econ. Rev. 2020, 31, 431–470. 
10. Bucevska, V. Currency Crises in EU Candidate Countries: An Early Warning System Approach. Panoeconomicus 2015, 62, 493–510.
11. Caggiano, G.; Calice, P.; Leonida, L. Early warning systems and systemic banking crises in low-income countries: A multinomial logit approach. J. Bank. Financ. 2014, 47, 258–269.
12. Candelon, B.; Dumitrescu, E.I.; Hurlin, C. Currency crisis early warning systems: Why they should be Dynamic. Int. J. Forecast. 2014, 30, 1016–1029.
13. Chang, Y.C.; Chang, K.H.; Wu, G.J. Application of eXtreme gradient boosting trees in the construction of credit risk assessment models for financial institutions. Appl. Soft Comput. 2018, 73, 914–920.
14. Chen, T.; Guestrin, C. XGBoost: A scalable tree boosting system. arXiv 2016
15. Charette, F.; d’Astous, A. Country Image Effects in the Era of Protectionism. J. Int. Consum. Mark. 2020, 32, 271–286.
16. Chaudhuri, A. Support Vector Machine Model for Currency Crisis Discrimination. arXiv 2014, arXiv:1403.04898.
17. Chang, R.Y.; Khan, H.A.; Lin, C.S.; Wang, Y.C. A new approach to modeling early warning systems for currency crises: Can a machine-learning fuzzy expert system predict the currency crises effectively? J. Int. Money Financ. 2008, 27, 1098–1121.
18. Dawood, M.; Horsewood, N.; Strobel, F. Predicting Sovereign Debt Crises: An Early Warning System Approach. J. Financ. Stab. 2017, 28, 16–28.
19. Di Nardo, M.; Castagna, F.; Madonna, M.; Murino, T. Modelling a Safety Management System Using System Dynamics at the Bhopal Incident. Appl. Sci. 2020, 10, 903.
20. Di Nardo, M.; Gallo, M.; Murino, T.; Santillo, L.C. System Dynamics Simulation for Fire and Explosion Risk Analysis in Home Environment. Int. Rev. Model. Simul. 2017, 10, 43–54.
21. Di Nardo, M. Developing a Conceptual Framework Model of Industry 4.0 for Industrial Management. Ind. Eng. Manag. Syst. 2020, 19, 551–560.
22. Dsoulia, O.; Khan, N.; Kakabadse, N.K.; Skouloudis, A. Mitigating the Davos dilemma: Towards a global self-sustainability index. Int. J. Sustain. Dev. World Ecol. 2018, 25, 81–98.
23. Dufrénot, G.; Paret, A.G. Sovereign debt in emerging market countries: Not all of them are serial defaulters. Appl. Econ. 2018, 50, 6406–6443.
24. Efimov, D.; Sulieman, H. Sobol Sensitivity: A Strategy for Feature Selection. In Mathematics across Contemporary Sciences; AUS-ICMS 2015; Springer Proceedings in Mathematics & Statistics; Springer: Cham, Switzerland, 2015;.
25. Feenstra, R.C.; Taylor, A.M. International Macroeconomics, 2nd ed.; Worth Publishers: New York, NY, USA, 2012.
26. Fioramanti, M. Predicting sovereign debt crises using artificial neural networks: A comparative approach. J. Financ. Stab. 2008, 4, 149–164. 
27. Fratzscher, M. On currency crises and contagion. Int. J. Financ. Econ. 2003, 8, 109–129. 
28. Fuertes, A.M.; Kalotychou, E. Optimal design of early warning systems for sovereign debt crises. Int. J. Forecast. 2007, 23, 85–100.
29. Kahneman, D., & Tversky, A. (1979). Prospect theory: An analysis of decision under risk. Econometrica, 47(2), 263-291.
30. Hastie, T.; Tibshirani, R.; Friedman, J. Random Forests. In The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed.; Springer: New York, NY, USA, 2009; pp. 587–603.
31. Hearst, M.; Schölkopf, B.; Dumais, S.; Osuna, E.; Platt, J. Trends and controversies–Support vector machines. IEEE Intell. Syst. 1998, 13, 18–28. 
32. Heidari, E.; Sobati, M.A.; Movahedirad, S. Accurate prediction of nanofluid viscosity using a multilayer perceptron artificial neural network (MLP-ANN). Chemom. Intell. Lab. Syst. 2016, 155, 73–85. 
33. Ho, T.K. Random decision forests. In Proceedings of the International Conference on Document Analysis and Recognition, Montreal, QC, Canada, 14–16 August 1995; IEEE Computer Society: Los Alamitos, CA, USA, 1995.
34. Jang, E.; Gu, S.; Poole, B. Categorical reparameterization with Gumbel-Softmax. arXiv 2016, arXiv:1611.01144.
35. Kalapanidas, E.; Avouris, N.; Craciun, M.; Neagu, D. Machine Learning Algorithms: A Study on Noise Sensitivity. In Proceedings of the First Balkan Conference in Informatics, Thessaloniki, Greece, 21–23 November 2003; pp.
36. Ibrahim, Y.; De Nisco, A.; Napolitano, M.R. The Role of Country Branding in Attracting Foreign Investment: Country Characteristics and Country Image. 
37. Kaminsky, G.; Lizondo, S.; Reinhart, C. Leading Indicators of Currency Crises; IMF Staff Papers; International Monetary Fund: Washington, DC, USA, 1998.
38. Koesel, K.J.; Steinberg, D.A.; Thompson, N.W. Political Regimes and Currency Crises.Econ. Politics 2015, 27, 337–361. 
39. Lai, K.K.; Wang, S.Y.; Yu, L. Currency Crisis Forecasting with General Regression Neural Networks. Int. J. Inf. Technol. Decis. Mak. 2006, 5, 437–454. 
40. Markowitz, H. (1952). Portfolio selection. The Journal of Finance, 7(1), 77-91.
41. Minsky, H. P. (1992). The financial instability hypothesis. The Jerome Levy Economics Institute Working Paper No. 74.
42. Manasse, P.; Roubini, N. “Rules of thumb” for sovereign debt crises. J. Int. Econ. 2009, 78, 192–205.
43. Manasse, P.; Roubini, N.; Schimmelpfennig, A. Predicting Sovereign Debt Crises (November 2003); IMF Working Paper, No. 03/221; International Monetary Fund: Washington, DC, USA, 2003; pp. 1–41.
44. Marghescu, D.; Sarlin, P. Visual predictions of currency crises using self-organizing maps. Intell. Syst. Account. Financ. Manag. 2011, 18, 15–38.
45. Melnyk, T.M.; Varibrusova, A.S. Variable indicators affecting the country’s brand strategy effectiveness and competitiveness in the world. Manag. Sci. Lett. 2019, 9, 1685–1700.
46. Núñez de Castro, L.; Von Zuben, F.J. Optimised Training Techniques for Feedforward Neural Networks; Technical Report DCA RT 03/98; Department of Computer Engineering and Industrial Automation, FEEC, UNICAMP: Campinas, Brazil, 1998.
47. Oztekin, A.; Bali, O.; Gumus, S.; Guresen, E.; Sevim, C. Developing an early warning system to predict currency crises. Eur. J. Oper. Res. 2014, 237, 1095–1104
48. Papadopoulos, N.; Ibrahim, Y.; De Nisco, A.; Napolitano, M.R. The Role of Country Branding in Attracting Foreign Investment: Country Characteristics and Country Image. 
49. Pham, T.H.A. Are global shocks leading indicators of currency crisis in Vietnam? Res. Int. Bus. Financ. 2017, 42, 605–615.
50. Popesku, J.; Teodorovi´c, M. Country Brand Equity Model: Sustainability Perspective. Marketing 2016, 47, 111–128. 
51. Prashanth, K.D.; Parthiban, P.; Dhanalakshmi, R. Evaluation and ranking of criteria affecting the supplier’s performance of a heavy industry by fuzzy AHP method. J. Sci. Ind. Res. 2018, 77, 268–270.
52. Raschka, S. Python Machine Learning; Packt Publishing Ltd.: Birmingham, UK, 2015.
53. Spence, M. (1973). Job market signaling. The Quarterly Journal of Economics, 87(3), 355-374.
54. Stiglitz, J. E. (2000). The contributions of the economics of information to twentieth century economics. The Quarterly Journal of Economics, 115(4), 1441-1478.