PDFDownload paper, RWP 20-14, October 2020; updated June 2022
We construct a new measure of monetary policy surprise based on a natural language processing algorithm designed to capture contextual nuances in FOMC statements. Specifically, we exploit cross-sectional variations across alternative FOMC statements to identify the statement's tone, and compare current and previous FOMC statements to obtain the novelty. We use high-frequency bond price movements around FOMC announcements to compute the surprise component of the monetary policy announcement. According to our measure, the stock market declines after unexpected policy tightening. Our text-based approach allows us to assess the counterfactual effects of an altered FOMC statement on the stock market.
JEL Classification: E30, E40, E50, G12
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