Makine Öğrenmesi Teknikleri ile Ülke Riski Tahmini
Country Risk Prediction with Machine Learning Techniques

Summary/Abstract: In a most general sense, country risk assessment is a measure of the foreign aid a country can receive and the risk the investors will face. Therefore, the related risk must be measured by making rather sensitive predictions with a procedure where economic, financial and political risks are taken into account. The prediction method must be chosen with great accuracy and supported with different methods. To that end, LRA, KNN, CART and DVM methods, which produce good estimation results and are frequently used, are preferred in country risk predictions. Different macroeconomic indicators of 75 countries between 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 considered and each machine learning algorithm is repeated 100 times, it is seen that the KNN algorithm is the best method to produce results. The following methods can respectively be listed as DVM, LRA and CART.

• Details
• Contents