Country Risk Prediction with Machine Learning Techniques

Yıl 2022, Cilt: 6 Sayı: 3, 1126 - 1151, 14.09.2022

Seyyide Doğan , Hasan Türe

https://doi.org/10.25295/fsecon.1098493

Cited By: 1

Öz

Country risk assessment, in the most general sense, is a measure of the foreign aid a country can receive and the risk the investors will face. Therefore, the related risk has to be measured by making rather sensitive predictions with a procedure where economical, financial and political risks are taken into account. The prediction method must be chosen with great accurateness and definitely supported with different methods. To that end, LRA, KNN, CART and DVM methods, which produce good estimation result and frequently used, are preferred in country risk predictions. Different macroeconomic indicators of 75 countries between the years 2015 and 2019 are used to train the prediction model. According to the findings of the study, it can be said that quite successful prediction results are produced with all the chosen methods. When different assessment criteria are taken into account and each machine learning algorithm are repeated 100 times, it is seen that the KNN algorithm is the best method to produce results. The following methods can be arrayed as DVM, LRA and CART.

Anahtar Kelimeler

country risk, machine learning, support vector machine, k-nearest neighbor, logistic regression, decision trees

Makine Öğrenmesi Teknikleri ile Ülke Riski Tahmini

Öz

Ülke riski değerlendirmesi en genel anlamıyla bir ülkenin alabileceği dış yardımların ve yatırımcıların karşı karşıya kalacağı riskin bir ölçüsüdür. Bu sebeple ülke riskinin, ekonomik, finansal ve politik risk unsurlarının birlikte ele alındığı bir prosedürle oldukça hassas tahminler yapılarak ölçülmesi gerekmektedir. Tahmin yöntemi büyük bir titizlikle tercih edilmeli ve mutlaka farklı yöntemler ile desteklenmelidir. Bu amaçla çalışmada, iyi tahmin sonuçları üreten ve sıklıkla kullanılan LRA, KNN, CART ve DVM yöntemleri tercih edilmiştir. Tahmin modelini eğitmek için 2015-2019 yılları arasında 75 ülkenin farklı makroekonomik göstergeleri kullanılmıştır. Çalışmanın bulgularına göre tercih edilen tüm yöntemler ile oldukça başarılı tahmin sonuçlarının üretildiği söylenebilir. Farklı değerlendirme kriterlerinin ele alındığı ve her bir makine öğrenmesi algoritmasının 100 kez tekrar edildiği durumda, en iyi sonucu veren yöntem KNN algoritması olduğu görülmektedir. Takip eden yöntemler ise sırası ile, DVM, LRA ve CART algoritması olarak sıralanabilir.

Anahtar Kelimeler

ülke riski, makine öğrenmesi, destek vektör makinesi, k-yakın komşuluk, lojistik regresyon, karar ağaçları

Kaynakça

• Abassi, B., & Taffler, R. J. (1982). Country Risk: A Model of Economic Performance Related to Debt Servicing Capacity. City University Business School.
• Abdou, H., Abdallah, W., Mulkeen, J., Ntim, C. G., & Wang, Y. (2017). Prediction of Financial Strength Ratings Using Machine Learning and Conventional Techniques. Investment Management and Financial Innovation, 14(4), 194-211.
• Alpaydın, E. (2011). Yapay Öğrenme, Boğaziçi Üniversitesi Yay. Birinci Basım.
• Amstad, M., Packer, F., 2015. Sovereign Ratings of Advanced and Emerging Economies After the Crisis, BIS Quarterly Review (December) Pp. 77–91.
• Arezki, R., Candelon, B., & Sy, A. N. R. (2011). Sovereign Rating News and Financial Markets Spillovers: Evidence from The European Debt Crisis. IMF Working Papers, 68.
• Asiri, B. K., & Hubail, R. A. (2014). An Empirical Analysis of Country Risk Ratings. Journal of Business Studies Quarterly, 5(4), 52.
• Balkan, E. M. (1992). Political İnstability, Country Risk and Probability of Default. Applied Economics, 24(9), 999-1008.
• Beirne, J., & Fratzscher, M. (2013). The Pricing of Sovereign Risk and Contagion During the European Sovereign Debt Crisis. Journal Of International Money and Finance, 34, 60-82.
• Bellotti, T., Matousek, R. And Stewart, C., 2011. A Note Comparing Support Vector Machines and Ordered Choice Models' Predictions Of İnternational Banks' Ratings. Decision Support System. 51(3), Pp. 682–687. https://Doi.Org/10.1016/J.Dss.2011.03.008
• Bennell, J. A., Crabbe, D., Thomas, S., & Ap Gwilym, O. (2006). Modelling Sovereign Credit Ratings: Neural Networks Versus Ordered Probit. Expert Systems with Applications, 30(3), 415-425.
• Berg, J., Clerc, L., Garnier, O., Nielsen, E. F., & Valla, N. (2015). From The İnvestment Plan to The Capital Markets Union: European Financial Structure and Cross Border Risk-Sharing. CEPII, Centr’ D'etudes Prospectives E’ D'informations İnternationales.
• Brauers, W. K., & Lepkova, N. (2019). Is Credit Rating Reserved Territory for Credit Rating Agencies? A MULTIMOORA Approach for European Firms and Countries. Technological And Economic Development of Economy, 25(6), 1259-1281.
• Breiman, L., Friedman, J., Olshen, R. And Stone, C. (1984). Classification and Regression Trees. 1984. Wadsworth & Brooks.
• Brewer, T. L., & Rivoli, P. (1990). Politics And Perceived Country Creditworthiness İn İnternational Banking. Journal Of Money, Credit and Banking, 22(3), 357-369.
• Broner, F., Martin, A., & Ventura, J. (2010). Sovereign Risk and Secondary Markets. American Economic Review, 100(4), 1523-55.
• Burges, C. J. C. (1998). A Tutorial on Support Vector Machines for Pattern Recognition, Data Mining and Knowledge Discovery: Kluwer Academic Publishers, Boston.
• Busse, M., & Hefeker, C. (2007). Political Risk, İnstitutions And Foreign Direct İnvestment. European Journal of Political Economy, 23(2), 397-415.
• Cantor, R., & Packer, F. (1996). Determinants and İmpact of Sovereign Credit Ratings. Economic Policy Review, 2(2).
• Cantor, R., & Packer, F. (1996). Multiple Ratings and Credit Standards: Differences of Opinion İn The Credit Rating İndustry (No. 12). Nueva York: Federal Reserve Bank Of New York.
• Cantor, R., & Packer, F. (1996-A). Multiple Ratings and Credit Standards: Differences of Opinion İn The Credit Rating İndustry (No. 12). Nueva York: Federal Reserve Bank Of New York.
• Cantor, R., & Packer, F. (1996-B). Determinants and İmpact of Sovereign Credit Ratings. Economic Policy Review, 2(2).
• Caporale, G. M., Matousek, R., & Stewart, C. (2011). EU Banks Rating Assignments: Is There Heterogeneity Between New And Old Member Countries?. Review Of International Economics, 19(1), 189-206.
• Chen, S., Härdle, W. K., & Moro, R. A. (2011). Modeling Default Risk with Support Vector Machines. Quantitative Finance, 11(1), 135-154.
• Cooper, J. C. (1999). Artificial Neural Networks Versus Multivariate Statistics: An Application from Economics. Journal Of Applied Statistics, 26(8), 909-921.
• Corsetti, G., Kuester, K., Meier, A., & Müller, G. J. (2013). Sovereign Risk, Fiscal Policy, And Macroeconomic Stability. The Economic Journal, 123(566), F99-F132.
• Cortes, C. And Vapnik, V. (1995). Support Vector Networks. Machine Learning, 20, 1-25.
• Cosset, J. C., & Roy, J. (1991). The Determinants of Country Risk Ratings. Journal Of International Business Studies, 22(1), 135-142.
• Cunha, I., Ferreira, M. A., & Silva, R. (2019). Do Credit Rating Agencies Influence Elections?. Available At SSRN 2748458.
• Dhonte, P. (1974). Quantitative İndicators And Analysis of External Debt Problems. International Monetary Fund Mimeo, Washington, DC.
• Diamonte, R. L., Liew, J. M., & Stevens, R. L. (1996). Political Risk İn Emerging and Developed Markets. Financial Analysts Journal, 52(3), 71-76.
• Doluca, H. (2014). Is There a Bias in Sovereign Ratings Due to Financial Reasons? The Empirical Economics Letters, 13 (7), 801 – 814.
• Doumpos, M., & Zopounidis, C. (2002). On The Use of A Multi‐Criteria Hierarchical Discrimination Approach For Country Risk Assessment. Journal Of Multi‐Criteria Decision Analysis, 11(4‐5), 279-289.
• Easton, S. T., & Rockerbie, D. W. (1999). What's İn A Default? Lending To LDCs İn The Face of Default Risk. Journal Of Development Economics, 58(2), 319-332.
• Edwards, S. (1985). The Pricing of Bonds and Bank Loans İn International Markets: An Empirical Analysis Of Developing Countries & Apos; Foreign Borrowing. NBER Working Paper, (W1689).
• Erdal, H. I., & Karakurt, O. (2013). Advancing Monthly Streamflow Prediction Accuracy of CART Models Using Ensemble Learning Paradigms. Journal Of Hydrology, 477, 119-128.
• Feder, G., & Just, R. E. (1977). A Study of Debt Servicing Capacity Applying Logit Analysis. Journal Of Development Economics, 4(1), 25-38.
• Fix, E., & Hodges, J. L. (1989). Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties. International Statistical Review/Revue Internationale De Statistique, 57(3), 238-247.
• Frank Jr, C. R., & Cline, W. R. (1971). Measurement Of Debt Servicing Capacity: An Application of Discriminant Analysis. Journal Of İnternational Economics, 1(3), 327-344.
• Frascaroli, B. F., & Oliveira, J. (2017). Sovereign Risk Ratings, Macroeconomic Fundamentals and Accountability: Evidence from Developing Countries. Advances İn Scientific and Applied Accounting, 304-318.
• Haan, J. D., Siermann, C. L., & Lubek, E. V. (1997). Political İnstability And Country Risk: New Evidence. Applied Economics Letters, 4(11), 703-707.
• Han, J. And Kamber, M. (2006). Data Mining Concepts and Techniques (2nd Edition).
• Haque, N. U., Kumar, M. S., Mark, N., & Mathieson, D. J. (1996). The Economic Content Of İndicators Of Developing Country Creditworthiness. Staff Papers, 43(4), 688-724.
• Haque, N.U., Mark, N. C., & Mathieson, D. J. (1998). The Relative İmportance Of Political and Economic Variables İn Creditworthiness Ratings.
• Hernández-Trillo, F. (1995). A Model-Based Estimation of The Probability of Default İn Sovereign Credit Markets. Journal Of Development Economics, 46(1), 163-179.
• Hilscher, J., & Nosbusch, Y. (2010). Determinants Of Sovereign Risk: Macroeconomics Fundamentals and The Pricing of Sovereign Debt. Review of Finance, 14(2), 235-262.
• Hoti, S., & Mcaleer, M. (2004). An Empirical Assessment of Country Risk Ratings and Associated Models. Journal Of Economic Surveys, 18(4), 539-588.
• Ivkin, A. (2018). Country Risk İn International Investment: Its’ Structure and Methods of Estimation. Review Of Business and Economics Studies, 6(1), 56-77.
• Khandani, A. E., Kim, A. J., & Lo, A. W. (2010). Consumer Credit-Risk Models Via Machine-Learning Algorithms. Journal Of Banking & Finance, 34(11), 2767-2787.
• Kharas, H. (1984). The Long-Run Creditworthiness of Developing Countries: Theory and Practice. The Quarterly Journal of Economics, 99(3), 415-439.
• Kobrin, S. J. (1979). Political Risk: A Review and Reconsideration. Journal Of İnternational Business Studies, 10(1), 67-80.
• Krayenbuehl, T. E. (1985) Country Risk: Assessment and Monitoring, Toronto: Lexington Books Kutty, G. (1990). Logistic Regression and Probability of Default of Developing Countries Debt. Applied Economics, 22(12), 1649-1660.
• Lanoie, P., & Lemarbre, S. (1996). Three Approaches to Predict the Timing and Quantity of LDC Debt Rescheduling. Applied Economics, 28(2), 241-246.
• Lee, S. H. (1993-A). Relative İmportance Of Political İnstability And Economic Variables on Perceived Country Creditworthiness. Journal Of International Business Studies, 24(4), 801-812.
• Lee, S. H. (1993-B). Are The Credit Ratings Assigned By Bankers Based On The Willingness Of LDC Borrowers To Repay?. Journal Of Development Economics, 40(2), 349-359.
• Li, J. P., Tang, L., Sun, X. L., He, W., & Yang, Y. Y. (2012). Country Risk Forecasting for Major Oil Exporting Countries: A Decomposition Hybrid Approach. Computers & Industrial Engineering, 63(3), 641-651.
• Liao, Y., Fang, S.-C., Nuttle, H.L.W. (2004). A Neural Network Model with Bounded-Weights for Pattern Classification. Computers And Operation Research.31,1411-1426.
• Lloyd-Ellis, H., Mckenzie, G. W., & Thomas, S. H. (1990). Predicting The Quantity of LDC Debt Rescheduling. Economics Letters, 32(1), 67-73.
• Lou, C., & Kou, G. (2012). A Time Series PROMETHEE Model for Sovereign Credit Default Risk Evaluation. International Journal of Advancements İn Computing Technology, 4(17).
• Moody’s Global Rating, Rating Symbols and Definitions 2.10.2021 Https://www.Moodys.Com/Researchdocumentcontentpage.Aspx?Docid=PBC_79004
• Nikolov, P. (2016). Cross-Border Risk Sharing After Asymmetric Shocks: Evidence from The Euro Area and The United States. Quarterly Report on The Euro Area (QREA), 15(2), 7-18.
• OECD. Country Risk Classifications of The Participants to The Arrangement on Officially Supported Export Credits, Organization for Economic Co-Operation and Development. Https://Www.Oecd.Org/Trade/Topics/Export-Credits/Arrangement-And-Sector-Understandings/Financing-Terms-And-Conditions/Country-Risk-Classification/E.T. 5.12.2021.
• Oetzel, J. M., Bettis, R. A., & Zenner, M. (2001). Country Risk Measures: How Risky Are They?. Journal Of World Business, 36(2), 128-145.
• Oral, M., Kettani, O., Cosset, J. C., & Daouas, M. (1992). An Estimation Model for Country Risk Rating. International Journal of Forecasting, 8(4), 583-593.
• Osisanwo, F. Y., Akinsola, J. E. T., Awodele, O., Hinmikaiye, J. O., Olakanmi, O., & Akinjobi, J. (2017). Supervised Machine Learning Algorithms: Classification and Comparison. International Journal of Computer Trends and Technology (IJCTT), 48(3), 128-138.
• Ozturk, H., Namli, E., & Erdal, H. I. (2016). Modelling Sovereign Credit Ratings: The Accuracy of Models İn A Heterogeneous Sample. Economic Modelling, 54, 469-478.
• Patel, N. D. And Upadhyay, S. (2012). "Study Of Various Decision Tree Pruning Methods with Their Empirical Comparison İn WEKA". International Journal of Computer Applications, 60, 20-25.
• Rahnama-Moghadam, M., Samavati, H., & Haber, L. J. (1991). The Determinants of Debt Rescheduling: The Case of Latin America. Southern Economic Journal, 510-517.
• Ramcharran, H. (1999). Foreign Direct İnvestment And Country Risk: Further Empirical Evidence. Global Economic Review, 28(3), 49-59.
• Rivoli, P., & Brewer, T. L. (1997). Political İnstability And Country Risk. Global Finance Journal, 8(2), 309-321.
• Scherer, K. P., & Avellaneda, M. (2002). All For One… One For All? A Principal Component Analysis of Latin American Brady Bond Debt From 1994 To 2000. International Journal of Theoretical and Applied Finance, 5(01), 79-106.
• Scholtens, B. (2004). Country Risk Analysis: Principles, Practices and Policies. In Sovereign Risk and Financial Crises (Pp. 3-27). Springer, Berlin, Heidelberg.
• Silva, D. R. B., Rêgo, T. G. D., & Frascaroli, B. F. (2019). Sovereign Risk Ratings’ Country Classification Using Machine Learning.
• Song, Y.-Y. And Lu, Y. (2015). "Decision Tree Methods: Applications for Classification and Prediction". Shanghai Archives of Psychiatry, 27, 130-135.
• Stankevičienė, J., & Sviderskė, T. (2012). Country Risk Assessment Based On MULTIMOORA. In 7th International Scientific Conference “Business and Management 2012” May 10-11, 2012, Vilnius, Lithuania.
• Stankevičienė, J., Sviderskė, T., & Miečinskienė, A. (2014). Dependence Of Sustainability On Country Risk İndicators İn EU Baltic Sea Region Countries. Journal Of Business Economics and Management, 15(4), 646-663.
• Sun, X., Feng, Q., & Li, J. (2021). Understanding Country Risk Assessment: A Historical Review. Applied Economics, 53(37), 4329-4341.
• Svilokos, T., & Rodić, M. (2015). Country Rısk Analysıs Based on Analytıc Hıerarchy Process. Poslovna İzvrsnost, 9(1), 0-0. Sy, A. N. R. (2009). The Systemic Regulation of Credit Rating Agencies and Rated Markets. World Economics Data Papers 10(4): 69-108.
• Tibshirani, R. (1996). "Regression Shrinkage and Selection Via the Lasso". Journal of The Royal Statistical Society. Series B (Methodological), 58, 267-288.
• Tichy, G., Lannoo, K., Ap Gwilym, O., Alsakka, R., Masciandaro, D., & Paudyn, B. (2011). Credit Rating Agencies: Part Of The Solution Or Part Of The Problem?. Intereconomics, 46(5), 232-262.
• Tiwari, A.K., 2017. Introduction To Machine Learning. Ubiquitous Mach. Learn. Its Appl. Https://Doi.Org/10.4018/978-1-5225-2545-5.Ch001.
• Türe, H., & Başer, F. (2015). Bulanık C-Ortalama Kümeleme Algoritması ile Ülke Risk Değerlendirmesi. Ekonometri ve İstatistik Dergisi, (23), 16-33.
• Türe, H., Koçak, D., & Doğan, S. (2017). MULTIMOORA Yöntemi İle Ülke Riski Değerlendirmesi. Gazi Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 18(3), 824-844.
• Van Gestel, T., Baesens, B., Van Dijcke, P., Garcia, J., Suykens, J. A., & Vanthienen, J. (2006). A Process Model to Develop An İnternal Rating System: Sovereign Credit Ratings. Decision Support Systems, 42(2), 1131-1151.
• Vapnik V. N., Chervonenkis, A. V. (1968). On The Uniform Convergence of Relative Frequencies of Events to Their Probabilities, Soviet Math. Dokl. 9,915-918. İngilizce Çeviri: 2015. In Measures of Complexity (11-30). Springer, Cham.
• Vij, M. (2005). The Determinants of Country Risk Analysis. Journal of Management Research, 5(1), 20-31.
• Wagenmans, F. (2017). Machine Learning İn Bankruptcy Prediction (Master's Thesis).
• Yim, J., & Mitchell, H. (2005). Comparison Of Country Risk Models: Hybrid Neural Networks, Logit Models, Discriminant Analysis and Cluster Techniques. Expert Systems with Applications, 28(1), 137-148.
• Zou, H. And Hastie, T. (2005). Regularization And Variable Selection Via the Elastic Net. Journal Of the Royal Statistical Society: Series B (Statistical Methodology), 67(2):301–320.