Jin-Kyu Jung, Manasa Patnam, and Anna Ter-Martirosyan
Forecasting macroeconomic variables is key to developing a view on a country's economic outlook.
Most traditional forecasting models rely on fitting data to a pre-specified relationship between input
and output variables, thereby assuming a specific functional and stochastic process underlying that
process. We pursue a new approach to forecasting by employing a number of machine learning
algorithms, a method that is data driven, and imposing limited restrictions on the nature of the true
relationship between input and output variables. We apply the Elastic Net, SuperLearner, and
Recurring Neural Network algorithms on macro data of seven, broadly representative, advanced and
emerging economies and find that these algorithms can outperform traditional statistical models,
thereby offering a relevant addition to the field of economic forecasting.
Which structural reforms affect the speed the regional convergence within a country? We found that domestic financial development, trade/current account openness, better institutional infrastructure, and selected labor market reforms facilitate regional convergence. However, these reforms have mixed effects on the growth of regions closer to the country’s development frontier. We also document that regional income disparity and average income are inversely correlated across countries so that speeding up regional convergence increases national income. We also present a theoretical model to discuss these results.