No abstract

No abstract

The deep-learning model outperforms the conventional structured models developed by using econometric techniques. Instead, econometric techniques provide an important insight into specific factors and their contribution to default probability. Using data from an Armenian universal credit organization that contains financial and nonfinancial variables of more than 9,000 borrowers of agriculture loans from 2012 to 2017 years, we compare deep neural networks' performance against conventional and widely used econometric techniques. Delays on past loans, together with loan size and currency, are major factors contributing to loan default probability prediction accuracy. The set of statistically significant or important variables differs between econometric and deep learning models proving that the latter can capture nonlinear relationships.

In spite of all previous efforts, the land border between Armenia and Turkey remains closed. Being one of the last reminders of the Cold War era, it significantly hinders the development of Armenia and eastern regions of Turkey. However, a closed border is more than a physical obstacle, as it also shapes the worldview and perceptions of the respective societies. Using the recent survey on “Public Opinion Poll: The Ways for Normalization of Armenian- Turkish Relations”, we identify the determinants of respondents’ attitudes towards the opening of the border. Among other results, we find that more awareness of the current Armenian-Turkish relationship increases the likelihood of the approval of the border. However, when selecting those respondents, who are either loyal to or approve the opening of the border, the awareness of the protocols’ content decreases the likelihood of the approval of the opening border. Our findings are supported by the contact theory which we use as a conceptual framework.