A1820
Title: A coherent framework for predicting emerging market credit spreads with support vector regression
Authors: Alena Audzeyeva - Keele University (United Kingdom)
Gary Anderson - CEMAR LLC (United States) [presenting]
Abstract: A coherent framework is proposed using support vector regression (SVR) for generating and ranking a set of high quality models for predicting emerging market sovereign credit spreads. Our framework adapts a global optimization algorithm employing a cross-validation metric for models with serially correlated variables, to produce robust sets of tuning parameters for SVR kernel functions. In contrast to previous approaches identifying a single best tuning parameter setting, we proceed with a collection of tuning parameter candidates, employing the Model Confidence Set test to select the most accurate models from the collection of promising candidates. Using bond credit spread data for three large emerging market economies and an array of input variables motivated by economic theory, we apply our framework to identify small sets of SVR models with superior out-of-sample forecasting performance. Benchmarking our SVR forecasts against random walk and conventional linear model forecasts provides evidence for the superior forecasting accuracy of SVR-based models. In contrast to linear model benchmarks, the SVR-based models can generate accurate forecasts using only the country-specific credit-spread-curve factors, lending some support to the rational expectation theory of the term structure in the context of emerging market credit spreads. Our evidence indicates a better ability of SVR to capture investor expectations about future spreads reflected in today's credit spread curve.
