Susan Athey (Stanford), Guido Imbens (Stanford), Greg Lewis (Microsoft) and Jann Spiess (Stanford GSB)
In recent years economists have started adopting and adapting machine learning methods that are revolutionizing data science for empirical analyses in economics. In this session we plan to bring together economists and econometricians interested in the use of machine learning methods in economics. We plan to include in the program both methodological papers developing methods for analyzing economic data and applicaPons of machine learning methods to economic problems, including applicaPons using reduced form and structural methods. The hope is to expose the methodologists to the type of questions empirical researchers are interested in, and to expose the empirical researchers to cutting edge methodologies. We intend to take a broad view of causal inference and machine learning, and include both experimental designs, as well as observaPonal studies and the use of non-standard data.