Multivariate macroeconomic forecasting: From DSGE and BVAR to artificial neural networks

This paper contributes a multivariate forecasting comparison between structural models and Machine-Learning-based tools. Specifically, a fully connected feed forward nonlinear autoregressive neural network (ANN) is contrasted to a well established dynamic stochastic general equilibrium (DSGE) model, a Bayesian vector autoregression (BVAR) using optimized priors as well as Greenbook and SPF forecasts. Model estimation and forecasting is based on an expanding window scheme using quarterly U.S. real-time data (1964Q2:2020Q3) for 8 macroeconomic time series (GDP, inflation, federal funds rate, spread, consumption, investment, wage, hours worked), allowing for up to 8 quarter ahead forecasts. The results show that the BVAR improves forecasts compared to the DSGE model, however there is evidence for an overall improvement of predictions when relying on ANN, or including them in a weighted average. Especially, ANNbased inflation forecasts improve other predictions by up to 50%. These results indicate that nonlinear data-driven ANNs are a useful method when it comes to macroeconomic forecasting.