Natural Language Processing: An Application in Public Policy

Description: In this project, I show an example analysis of using topic modelling to extract topics from the Federal Reserve Board of Governors’s policy statements released after each policy meeting. We extract topics and look at the importance of these topics in contributing to stock market volatility. I demonstrate principles in text preprocessing, topic modelling, evalutating topic models, visualizing the results, and statistical modelling.

The Github repository for this project can be found here.

Avatar
Ancil Crayton
Senior Research Scientist

My research interests lie at the intersection of machine learning, economic analysis, and public policy.