*In Colombia, numerous anti-drug policies have been implemented, including the controversial use of glyphosate through aerial spraying as a national policy. However, the potential impact of this policy on the civil population remains largely unknown. We investigate the effect of aerial eradication on educational outcomes. We use a sharp regression discontinuity design that combines school census data with newly digitized maps from the Integrated Monitoring System of Illicit Crops. Our preliminary findings indicate that aerial spraying leads to an 7% increase in the dropout rate and a 6% increase in the fail rate, compared to the control group. Furthermore, we observe that this shock primarily affects early child human capital accumulation. We document that the income shock is the likely mechanism for the observed effect.

**We nowcast world trade using machine learning, distinguishing between tree-based methods (random forest, gradient boosting) and their regression-based counterparts (macroeconomic random forest, gradient linear boosting). While much less used in the literature, the latter are found to outperform not only the tree-based techniques, but also more “traditional” linear and non-linear techniques (OLS, Markov-switching, quantile regression). They do so significantly and consistently across different horizons and real-time datasets. To further improve performances when forecasting with machine learning, we propose a flexible three-step approach composed of (step 1) pre-selection, (step 2) factor extraction and (step 3) machine learning regression. We find that both pre-selection and factor extraction significantly improve the accuracy of machine-learning-based predictions. This three-step approach also outperforms workhorse benchmarks, such as a PCA-OLS model, an elastic net, or a dynamic factor model. Finally, on top of high accuracy, the approach is flexible and can be extended seamlessly beyond world trade.