Trying to beat analytical models with LLMs in the stock market
A trading-agent experiment that started with FINSABER, wrapped ARIMA-style signals in Mercury 2, and ended with the analytical baseline winning.
A trading-agent experiment that started with FINSABER, wrapped ARIMA-style signals in Mercury 2, and ended with the analytical baseline winning.
Give the model real context, generate less, and delete anything that explains what the reader can already see.
Astro, Markdown, GitHub Pages, Cloudflare, and a publishing flow I can use from ChatGPT on my phone.