A Machine Learning Approach to Forecast Economic Recessions—An Italian Case Study

Abstract

Abstract:In economic activity , recessions represent a period of failure in Gross Domestic Product (GDP) and usually are presented as episodic and non-linear. For this reason, they are difficultto predictandappearasoneofthemainproblemsinmacroeconomicsforecasts.Aclassicexample turnsouttobethegreatrecessionthatoccurredbetween2008and2009thatwasnotpredicted. Inthispaper,thegoalistogiveadifferent,althoughcomplementary,approachconcerningthe classical econometric techniques, and to show how Machine Learning (ML) techniques may improve short-term forecasting accuracy . As a case study , we use Italian data on GDP and a few related variables. In particular, we evaluate the goodness of fitoftheforecastingproposedmodelina case study of the Italian GDP . The algorithm is trained on Italian macroeconomic variables over the period 1995:Q1-2019:Q2. We also compare the results using the same dataset through Classic Linear Regression Model. As a result, both statistical and ML approaches are able to predict economic downturns but higher accuracy is obtained using Nonlinear Autoregressive with exogenous variables (NARX) model.

Tasks

Reproductions