Capturing international influences in U.S. monetary policy through a NLP approach

Officially, the U.S. Federal Reserve has a statutory dual domestic mandate of price stability and full employment, but, in this paper, we question the role of the international environment in shaping Fed monetary policy decisions. In this respect, we use minutes of the Federal Open Market Committee (FOMC) and construct indexes of the attention paid by U.S. monetary policymakers to the international economic and financial situation. These indexes are built by applying natural language processing (NLP) techniques ranging from word count to built-from-scratch machine learning models, to OpenAI's GPT models. By integrating those text-based indicators into a Taylor rule, we derive various quantitative measures of the external influences on Fed decisions. Our results show that when there is a focus on international topics within the FOMC, the Fed’s monetary policy generally tends to be more accommodative than expected by a standard Taylor rule. This result is robust to various alternatives that includes a time-varying neutral interest rate or a shadow central bank interest rate.