Identifying Monetary Policy Shocks: A Natural Language Approach

We develop a novel method for the identification of monetary policy shocks. By applying natural language processing techniques to documents that Federal Reserve staff prepare in advance of policy decisions, we capture the Fed’s information set. Using machine learning techniques, we then predict changes in the target interest rate conditional on this information set and obtain a measure of monetary policy shocks as the residual. We show that the documents’ text contains essential information about the economy which is not captured by numerical forecasts that the staff include in the same documents. The dynamic responses of macro variables to our monetary policy shocks are consistent with the theoretical consensus. Shocks constructed by only controlling for the staff forecasts imply responses of macro variables at odds with theory. We directly link these differences to the information that our procedure extracts from the text over and above information captured by the forecasts.