Authors: Emmanouil Sofianos, Theophilos Papadimitriou, Periklis Gogas

Title: Forecasting Euro-Area Output Gaps with Machine Learning and Interest Rates

Abstract

The fluctuations from the trend of the GDP (output gaps) signify that the economy is either overworking or underworking its resources, thus the ability to forecast them accurately in time is of great interest to policy-makers in both the government and the central bank. They can implement the necessary fiscal and monetary policy to minimize these deviations from the potential (trend) output. In this research, we use the Eurozone yield curve in an effort to forecast the deviations of the euro-area output (IPI) from its long-run trend. We use various short- and long-term interest rates spanning the period from 2004:9 to 2020:6 in monthly frequency. The interest rates are fed to three machine learning methodologies: Decision Trees, Random Forests, and Support Vector Machines (SVM). These Machine Learning methodologies are then compared to an Elastic-Net Logistic Regression (Logit) model from the area of Econometrics. According to the results, the optimal SVM model coupled with the RBF kernel outperforms the competition reaching an in-sample accuracy of 85.29% and an out-of-sample accuracy of 94.74%.