Dr. Christopher RauhUniversity of Cambridge and Trinity College Cambridge, UK
Speech Title: Creating Risk Measures Using Vast Amounts of Text
Abstract: We predict the risk of political violence using a newspaper-text corpus of more than 5 million articles. We derive topics from text through unsupervised machine learning and then integrate these topics into a supervised machine learning framework to forecast risk.
Biography: Christopher is a Lecturer at the University of Cambridge, a Fellow of Trinity College Cambridge, and a Research Affiliate at CEPR. Before joining the University of Cambridge, he was an Assistant Professor at the University of Montreal. He is also an Associate Editor of the Economic Journal.
Christopher studies policy-relevant questions related to the labor market and political economy. He has designed many survey modules and collected primary data. He also works with complex datasets and applied methodologies, including machine learning and structural modelling.
He has published in top Economics and Political Science journals, such as American Political Science Review, Journal of European Economic Association, and Journal of Public Economics. His work has been featured widely across the media including The Guardian, China Global Television Network, Washington Post, the Economist, the BBC, and Der Spiegel. He is listed amongst the top 3% of Economists in terms of research output in the last ten years.