Text-Based Recession Probabilities

This paper proposes a new methodology based on textual analysis to forecast US recessions. Specifically, it presents an index in the spirit of Baker et al. (JAMA 131:1593-1636, 2016) and Caldara and Iacoviello (JAMA 1222, 2018) that tracks developments in US real activity. When used in a standard recession probability model, this index outperforms the yield curve-based forecast, a standard method to forecast recessions, at medium horizons, up to 8 months. Moreover, the index contains information not included in yield data, that are useful to understand recession episodes; when included as an additional control along with the slope of the yield curve, it improves forecasting accuracy by between 5% and 40%, depending on the horizon considered. These results are stable to a number of different robustness checks, including different estimation methods, different definitions of recession and controlling for asset purchases by major central banks. Our textual analysis data also improve the forecasting accuracy of several other popular leading indicators for the US business cycle.