TY - BOOK ID - 137672004 TI - Deus ex Machina? A Framework for Macro Forecasting with Machine Learning AU - Bolhuis, Marijn. AU - Rayner, Brett. PY - 2020 SN - 1513536532 PB - Washington, D.C. : International Monetary Fund, DB - UniCat KW - Turkey KW - Econometrics KW - Forecasting KW - Intelligence (AI) & Semantics KW - Forecasting and Other Model Applications KW - Neural Networks and Related Topics KW - Classification Methods KW - Cluster Analysis KW - Principal Components KW - Factor Models KW - Technological Change: Choices and Consequences KW - Diffusion Processes KW - Econometrics & economic statistics KW - Machine learning KW - Economic Forecasting KW - Factor models KW - Economic forecasting KW - Econometric analysis KW - Technology KW - Econometric models UR - https://www.unicat.be/uniCat?func=search&query=sysid:137672004 AB - 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 transparency 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. ER -