Forecasting Sovereign Credit Ratings Using Differential Evolution and Logic Aggregation in IBA Framework

Abstract

The sovereign credit rating is considered as a quantified assessment of country's economic and political stability. Due to its importance and increasing amount of available information, the sovereign credit rating is considered as a hot topic in the last few years. However, the models that predict the credit ratings used by the several big credit rating agencies are unavailable, and can therefore be considered as the black boxes. In this paper, we are tackling this problem of predicting sovereign credit ratings by proposing a hybrid model based on interpolative Boolean algebra (IBA) and differential evolution (DE). Namely, we aim to obtain a logical/pseudo-logical function in IBA framework using DE metaheuristic that could underline connections of chosen macroeconomic indicators and sovereign credit ratings. Such functions are easy to interpret and able to make a subtle fuzzy gradation among countries. Country's economic indicators together with credit ratings from 2000 to 2016 are used for the model training. Acquired model is further tested on the data for 2017 and 2018.