Python for Finance, 3rd Edition

Chapter 16. NLP and LLM Foundations

A Note for Early Release Readers

With Early Release ebooks, you get books in their earliest form—the author’s raw and unedited content as they write—so you can take advantage of these technologies long before the official release of these titles.

This will be the 16th chapter of the final book. Please note that the GitHub repo will be made active later on.

If you’d like to be actively involved in reviewing and commenting on this draft, please reach out to the editor at [e-mail].

Most financial information is created and shared as text: news headlines, regulatory filings, earnings call transcripts, research reports, social-media posts, and even internal chat logs. Natural-language processing (NLP) provides tools for turning this unstructured text into numerical representations that can feed into the models you developed in the previous chapter. Large language models (LLMs) extend these ideas with powerful pretrained transformers that can summarize, classify, and extract structure from text with relatively little task-specific code.

This chapter builds a practical bridge from raw text to numerical features, and from classical NLP pipelines to modern LLM workflows. You start with simple tokenization and bag-of-words models, move on to dense embeddings and linear classifiers, and then use pretrained transformers and LLMs as flexible building blocks for semantic search and extraction tasks. Throughout, the focus is on realistic but ...