In this study, the possibilities of ranking or classifying countries, which are generally made using panel data analysis, are investigated using artificial intelligence models. For this, countries are classified in terms of unemployment, inflation, GDP Growth Rate, 5-year GDP Growth Rate, Foreign Direct Investment (FDI) Input and Job Freedom. Artificial Neural Networks (ANN), Support Vector Machines (SVM) and statistically Logistic Regression (LR) methods were used for classification. In the analyzes repeated ten times, LR (average 62.4%) gave the best result and SVM (2%) gave the lowest standard deviation.
The results obtained are promising for modern methods, but modern artificial intelligence methods, which have become an alternative to traditional methods in almost every field, are still behind traditional methods in this field. In order for modern methods to be an alternative to traditional methods in this regard, they need to further develop their theories (on matters such as the curse of dimension) or adapt the data structures used on the subject to these methods.
Primary Language | English |
---|---|
Subjects | International Economics (Other) |
Journal Section | Research Articles |
Authors | |
Early Pub Date | December 27, 2023 |
Publication Date | December 30, 2023 |
Submission Date | October 20, 2023 |
Acceptance Date | November 27, 2023 |
Published in Issue | Year 2023 Volume: 1 Issue: 1 |
Ekonomi Yönetim Politika Creative Commons Atıf-GayriTicari 4.0 Uluslararası Lisansı (CC BY NC) ile lisanslanmıştır.