Titolo della tesi: Essays on Machine Learning approaches to Causality and Forecasting
This thesis offers an extensive and detailed examination of machine learning estimators, coupled with innovative data sources and auxiliary techniques, within the context of forecasting and causal analysis. Across three comprehensive chapters, it delves into an analysis of current literature, presents original concepts and methodologies, and sheds light on the potential effects and implications these techniques may have in their respective fields, particularly through the lens of empirical applications. The objective of this work is to serve as an invaluable resource for a diverse audience, including researchers, policymakers, and anyone interested in gaining a deeper understanding of the dynamic and evolving nature of forecasting and causal inference in an era characterised by an ever-increasing abundance of data and ever-growing and pivotal role of machine learning in advancing the field of econometrics.