Text Data in Finance

The last several years have seen an enormous increase in the use of text data to supplement traditional financial decision making. All major sell side and buy side firms, as well as financial data providers, like S&P Global, Moody's, and Bloomberg, now devote significant resources to the processing of text data sets. These include news, earnings calls, Fed and other central bank communications, and social media. The ongoing adoption of large language models in many areas of finance makes understanding the tools of natural language processing (NLP) all the more pressing. This course introduces students to state of the art NLP methods and their applications to traditional problems in financial economics. The course is Python-based, analytically rigorous, and emphasizes the use of open-source NLP libraries. Students with a background in NLP will find the course useful because it will apply these tools to economics and finance questions. Students with a background in economics or finance will find the course useful because it will introduce modern NLP tools. The material from the course will be useful for either research or industry tasks. Past students have found the course extremely useful for their industry responsibilities.