Applied AI · Final-year project
Investor relations scraper.
A Python research tool for finding investor relations documents from a company website.
From a homepage to a document
A researcher can start with a company’s main website while the report they need sits several links away in its investor relations section. My final-year project tackled that discovery step. The Python scraper takes the company URL, fetches its HTML and uses an LLM to help locate investor relations documents.
Final-year report
I compared GPT-4.1 and Claude Sonnet 4.6 on the task of retrieving SEC filings from corporate investor relations websites.