Three Essays in Macroeconomics with a Focus on Forecasting GDP Growth with Machine Learning, Measuring Uncertainty with NLP, and Revisiting a Small Open Economy RBC Model

Chapter 1, entitled "Forecasting Canadian GDP Growth with Machine Learning," shows that it is possible to forecast Canadian monthly real GDP growth accurately ahead of the official release of GDP figures by Statistics Canada, by using, as predictors, Google trends (GT) data together with some Official data (such as employment) which are available before the official release of GDP data.This chapter uses some of the most recent supervised machine learning (ML) algorithms in order to forecast real GDP growth.The success of a supervised ML algorithm depends on its capability to capture nonlinearities in the relationship between the response variable and predictive variables as well as in the interactions between two predictive variables.Accordingly, in forecasting real GDP growth, we use nonlinear tree-based ensemble algorithms that have not been fully explored for economic forecasting, namely, eXtreme Gradient Boosting (XGBoost), CatBoost, Random Forest (RF) and Microsoft's Light Gradient Boosting Machine (LightGBM).We also use the nonlinear Support Vector Machine (SVM) algorithm, one of the best-known supervised ML algorithms for classification and regression analysis, which makes use of the nonlinear radial basis function as the kernel function.We use three data sets, namely, Official data, GT data and Official+GT data (a combination of the preceding two data sets).Feature selection is performed by either PDC-SIS, a variable selection procedure recently developed by Yousuf and Feng (2022) or XGBoost's "variable importance" measure (VI-XGBoost).The pre-selected features are then used together with the ML Bibliography

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.