Suchergebnisse

AbstractThe 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.

This report examines the social policy response of the Government of Armenia to the Covid-19 crisis. Official data on the implemented programs suggest that since March 2020, around USD 55 million has been transferred to individuals and households as wage support, unemployment and family benefits, utility payment subsidies and tuition fee support. Survey data suggest that despite being early and extensive, government assistance has not been effective in relieving the financial stress and anxiety caused by the pandemic, while public expectations about the future remain pessimistic. As individuals most and least in need have benefited equally from the implemented programs, government assistance has also not been well-targeted.