Artificial neural networks for macroeconomic data analysis

Abstract

The analysis and prediction of macroeconomic time-series is a factor of great interest to national policymakers. However, economic analysis and forecast- ing are not simple tasks due to the lack of a precise model for the economy and the influence of external factors, such as weather changes or political decisions. Our research is focused on Spanish speaking countries. In this thesis, we study dif- ferent types of neural networks and their applicability for various analysis tasks, including GDP prediction as well as assessing major trends in the development of the countries. The studied models include multilayered neural networks, recur- sive neural networks, and Kohonen maps. Historical macroeconomic data across 17 Spanish speaking countries, together with France and Germany, over the time period of 1980-2015 is analyzed. This work then compares the performances of various algorithms for training neural networks, and demonstrates the revealed changes in the state of the countries' economies. Further, we provide possible reasons that explain the found trends in the data.