RWP 20-14, October 2020; updated November 2023
We present a text-based metric for monetary policy stance using official and alternative Federal Open Market Committee statements. Our advanced natural language processing, with numeric property detection, jointly evaluates quantitative decisions like interest rates and qualitative explanations for these choices from texts. Monetary policy stance is decomposed into expected stance and surprise components by leveraging high-frequency bond futures data around FOMC announcements. We examine responses of stock returns to counterfactual (more dovish or hawkish) policy surprises through alternative language. This investigation yields valuable insights into monetary policy transmission.
JEL Classification: E30, E40, E50, G12
Article Citation
Doh, Taeyoung, Dongho Song, and Shu-Kuei Yang. 2020. “Deciphering Federal Reserve Communication via Text Analysis of Alternative FOMC Statements.” Federal Reserve Bank of Kansas City, Research Working Paper no. 20-14, October. Available at External Linkhttps://doi.org/10.18651/RWP2020-14