The data listed in the economic calendar comes from government and non-governmental entities and consists of largely macroeconomic numbers corresponding to GDP. Furthermore, having an concept of what the economic business cycle is and the way different stages of the cycle can have an effect on the costs of a wide range of assets provides an economics-savvy investor an edge when working in nearly any financial market. We suggest an approach to measuring the state of the economy via textual analysis of business news. From the full text content of 800,000 Wall Street Journal articles for , we estimate a topic mannequin that summarizes business news as simply interpretable topical themes and quantifies the proportion of reports attention allocated to each theme at every time limit. We then use our news consideration estimates as inputs into statistical models of numerical economic time series. We show that these textual content-based inputs precisely track a variety of economic activity measures and that they have incremental forecasting energy for macroeconomic outcomes, above and beyond standard numerical predictors. Finally, we use our mannequin to retrieve the news-based mostly narratives that underly “shocks” in numerical economic data.
Looking on the pace with which the disaster …
