Nowcasting GDP using machine-learning algorithms: A real-time assessment

Abstract 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.

[1]  J. Stock,et al.  Macroeconomic Forecasting Using Diffusion Indexes , 2002 .

[2]  C. Bloor.  The use of statistical forecasting models at the Reserve Bank of New Zealand , 2009 .

[3]  Tim Ng,et al.  Forecasting National Activity Using Lots of International Predictors: An Application to New Zealand , 2011, SSRN Electronic Journal.

[4]  F. Dias,et al.  Determining the number of factors in approximate factor models with global and group-specific factors , 2008 .

[5]  David H. Small,et al.  Nowcasting: the real time informational content of macroeconomic data releases , 2008 .

[6]  Evangelos Spiliotis,et al.  Statistical and Machine Learning forecasting methods: Concerns and ways forward , 2018, PloS one.

[7]  M. Medeiros,et al.  Linear models, smooth transition autoregressions, and neural networks for forecasting macroeconomic time series: A re-examination , 2005 .

[8]  Xiaowen Jin,et al.  Forecasting and Nowcasting Real GDP: Comparing Statistical Models and Subjective Forecasts , 2012 .

[9]  Amir F. Atiya,et al.  An Empirical Comparison of Machine Learning Models for Time Series Forecasting , 2010 .

[10]  Xiaowen Jin,et al.  Forecasting and Nowcasting Real GDP: Comparing Statistical Models and Subjective Forecasts , 2012 .

[11]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[12]  J. Bai,et al.  Determining the Number of Factors in Approximate Factor Models , 2000 .

[13]  P. McNelis,et al.  Forecasting Inflation with Thick Models and Neural Networks , 2004 .

[14]  D. Giannone,et al.  Now-Casting and the Real-time Data Flow , 2012, SSRN Electronic Journal.

[15]  Christian Pierdzioch,et al.  Predicting Recessions With Boosted Regression Trees , 2017 .

[16]  Paolo Fornaro,et al.  Nowcasting Finnish real economic activity: a machine learning approach , 2019, Empirical Economics.

[17]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[18]  Aaron Smalter Hall,et al.  Macroeconomic Indicator Forecasting with Deep Neural Networks , 2017 .

[19]  Troy D. Matheson.  Factor Model Forecasts for New Zealand , 2006 .

[20]  Bernhard Schölkopf,et al.  A Short Introduction to Learning with Kernels , 2002, Machine Learning Summer School.

[21]  Laura Coroneo,et al.  Comparing predictive accuracy in small samples , 2015 .

[22]  S. Gunn.  Support Vector Machines for Classification and Regression , 1998 .

[23]  Georgios Sermpinis,et al.  Inflation and Unemployment Forecasting with Genetic Support Vector Regression , 2014 .

[24]  Theophilos Papadimitriou,et al.  Forecasting the U.S. Real House Price Index , 2014 .

[25]  Jon Faust,et al.  Comparing Greenbook and Reduced Form Forecasts Using a Large Realtime Dataset , 2007 .

[26]  Kyoung-jae Kim,et al.  Financial time series forecasting using support vector machines , 2003, Neurocomputing.

[27]  D. Romer,et al.  The FOMC Versus the Staff: Where Can Monetary Policymakers Add Value? , 2008 .

[28]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[29]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.