Member-only story
Earnings Echoes: Can Words Predict Stock Returns? [Part 1/2]
A study into how earnings transcripts in combination with NLP can predict stock price performance
Disclaimer: The Content is for informational purposes only, you should not construe any such information or other material as legal, tax, investment, financial, or any other professional advice.
Introduction
In my previous story, I explored how you can utilize the LDA Topic Modeling algorithm to explore the topics mentioned in an earnings call. In this story, I will go a different direction. Instead of extracting the key topics in a scalable manner, we will explore how we can take the same data and build a predictive model.
For this article, I will use Python for modeling and the Financial Modeling Prep API for the data. After going through this story, if you are interested in this API and want to utilize this data for yourself, please sign up here!
Libraries and Data
The key libraries in this project include nltk and spacy for natural language processing and sklearn for the actual modeling.
We will use the Earnings Transcript endpoint from the Financial Modeling Prep API and the historical price endpoint for…
