Capturing international influences in U.S. monetary policy through a Natural Language Processing approach
中文摘要
我们考察国际环境在美联储货币政策形成中所起的作用,这一作用超出了其国内双重使命的范畴。我们利用联邦公开市场委员会的会议纪要,构建了美国货币政策制定者对国际经济与金融形势关注程度的指数。这些指数通过应用自然语言处理 (NLP) 技术构建,涵盖从词频统计到从头构建的机器学习模型(包括大语言模型)等多种方法。通过将这些基于文本的指标纳入泰勒规则,我们对美联储决策中的国际关注渠道进行了定量评估。我们的结果表明,国际关注度的提高——在我们的样本中,这种提高集中于海外出现不利事态发展之时——与比标准泰勒规则所隐含的更为宽松的货币政策立场相关。
Abstract
We examine the role of the international environment in shaping Federal Reserve monetary policy beyond its domestic dual mandate. We use minutes of the Federal Open Market Committee 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, including large language models. By integrating those text-based indicators into a Taylor rule, we get a quantitative assessment of the international attention channel on Fed decisions. Our results show that heightened international attention, which in our sample is concentrated around adverse foreign developments, is associated with a more accommodative monetary policy stance than implied by a standard Taylor rule.