Deus ex Machina? A Framework for Macro Forecasting with Machine Learning

Brett Rayner, Marijn Bolhuis
2020 IMF Working Papers  
We develop a framework to nowcast (and forecast) economic variables with machine learning techniques. We explain how machine learning methods can address common shortcomings of traditional OLS-based models and use several machine learning models to predict real output growth with lower forecast errors than traditional models. By combining multiple machine learning models into ensembles, we lower forecast errors even further. We also identify measures of variable importance to help improve the
more » ... ansparency of machine learning-based forecasts. Applying the framework to Turkey reduces forecast errors by at least 30 percent relative to traditional models. The framework also better predicts economic volatility, suggesting that machine learning techniques could be an important part of the macro forecasting toolkit of many countries. JEL Classification Numbers: C53, C45.
doi:10.5089/9781513531724.001 fatcat:gprwjc2fpncnrmtvozdwaqsjyi