TY - JOUR
T1 - Nowcasting GDP using machine-learning algorithms
T2 - A real-time assessment
AU - Richardson, Adam
AU - van Florenstein Mulder, Thomas
AU - Vehbi, Tuğrul
N1 - Publisher Copyright:
© 2020 International Institute of Forecasters
PY - 2021/4/1
Y1 - 2021/4/1
N2 - Can machine-learning algorithms help central banks understand the current state of the economy? Our results say yes! We contribute to the emerging literature on forecasting macroeconomic variables using machine-learning algorithms by testing the nowcast performance of common algorithms in a full ‘real-time’ setting—that is, with real-time vintages of New Zealand GDP growth (our target variable) and real-time vintages of around 600 predictors. Our results show that machine-learning algorithms are able to significantly improve over a simple autoregressive benchmark and a dynamic factor model. We also show that machine-learning algorithms have the potential to add value to, and in one case improve on, the official forecasts of the Reserve Bank of New Zealand.
AB - Can machine-learning algorithms help central banks understand the current state of the economy? Our results say yes! We contribute to the emerging literature on forecasting macroeconomic variables using machine-learning algorithms by testing the nowcast performance of common algorithms in a full ‘real-time’ setting—that is, with real-time vintages of New Zealand GDP growth (our target variable) and real-time vintages of around 600 predictors. Our results show that machine-learning algorithms are able to significantly improve over a simple autoregressive benchmark and a dynamic factor model. We also show that machine-learning algorithms have the potential to add value to, and in one case improve on, the official forecasts of the Reserve Bank of New Zealand.
KW - Forecast evaluation
KW - Forecasting practice
KW - Machine learning
KW - Macroeconomic forecasting
KW - Nowcasting
UR - http://www.scopus.com/inward/record.url?scp=85096533681&partnerID=8YFLogxK
U2 - 10.1016/j.ijforecast.2020.10.005
DO - 10.1016/j.ijforecast.2020.10.005
M3 - Article
SN - 0169-2070
VL - 37
SP - 941
EP - 948
JO - International Journal of Forecasting
JF - International Journal of Forecasting
IS - 2
ER -