GLOBAL PATTERNS AND EXTREME EVENTS IN SOVEREIGN RISK PREMIA: A FUZZY S DEEP LEARNING COMPARATIVE

Abstract

Investment in foreign countries has become more common nowadays and this implies that there may be risks inherent to these investments, being the sovereign risk premium the measure of such risk. Many studies have examined the behaviour of the sovereign risk premium, nevertheless, there are limitations to the current models and the literature calls for further investigation of the issue as behavioural factors are necessary to analyse the investor’s risk perception. In addition, the methodology widely used in previous research is the regression model, and the literature shows it as scarce yet. This study provides a model for a new of the drivers of the government risk premia in developing countries and developed countries, comparing Fuzzy methods such as Fuzzy Decision Trees, Fuzzy Rough Nearest Neighbour, Neuro-Fuzzy Approach, with Deep Learning procedures such as Deep Recurrent Convolution Neural Network, Deep Neural Decision Trees, Deep Learning Linear Support Vector Machines. Our models have a large effect on the suitability of macroeconomic policy in the face of foreign investment risks by delivering instruments that contribute to bringing about financial stability at the global level.