Template-type: ReDIF-Paper 1.0
Author-Name: Milen Arro-Cannarsa
Author-Name-First: Milen
Author-Name-Last: Arro-Cannarsa
Author-Name: Rolf Scheufele
Author-Name-First: Rolf
Author-Name-Last: Scheufele
Author-Person: psc357
Title: Nowcasting GDP: what are the gains from machine learning algorithms?
Abstract: We compare several machine learning methods for nowcasting GDP. A large mixed-frequency data set is used to investigate different algorithms such as regression based methods (LASSO, ridge, elastic net), regression trees (bagging, random forest, gradient boosting), and SVR. As benchmarks, we use univariate models, a simple forward selection algorithm, and a principal components regression. The analysis accounts for publication lags and treats monthly indicators as quarterly variables combined via blocking. Our data set consists of more than 1,100 time series. For the period after the Great Recession, which is particularly challenging in terms of nowcasting, we find that all considered machine learning techniques beat the univariate benchmark up to 28 % in terms of out-of-sample RMSE. Ridge, elastic net, and SVR are the most promising algorithms in our analysis, significantly outperforming principal components regression.

Length: 38 pages
Creation-Date: 2024
Contact-Email: forschung@snb.ch
File-URL: https://www.snb.ch/en/publications/research/working-papers/2024/working_paper_2024_06
File-Format: text/html
Number: 2024-06
Classification-JEL: C53, C55, C32, C37
Keywords: Nowcasting, Forecasting, Machine learning, Rridge, LASSO, Elastic net, Random forest, Bagging, Boosting, SVM, SVR, Large data sets
Handle: RePEc:snb:snbwpa:2024-06