Experiments in AI-driven financial analysis. We apply large language models to real research questions, publishing the methodology and results as open case studies.
Learn How It WorksA transparent record of AI tools applied to financial research questions that traditionally required large analyst teams. Each experiment is a genuine research exercise, not a product demonstration.
We publish our methodology and results in full, good or bad. If an experiment underperforms, that's part of the record.
Nothing published here constitutes investment advice or a recommendation to buy or sell any security. All portfolio tracking is on paper, with no capital involved.
The Fery Group is not a registered investment adviser. Always consult a licensed professional for investment decisions.
Every experiment starts with a specific, falsifiable claim stated before any data is analyzed.
AI prompts, data sources, scoring frameworks, and selection criteria are published in full on each experiment page.
Positions are tracked in real time against a benchmark. No results are cherry-picked or back-filled.
At close, we publish a full analysis: what the AI got right, what it missed, and whether the methodology has practical value.
Research purposes only. Analytical exercises using AI applied to public financial data. No real capital is deployed. Nothing here constitutes investment advice. Past performance of any methodology does not guarantee future results.