Ethan Buttery
Projects in AI and quantitative finance: systems that make investment decisions, and the tests that show whether they really work.
Everything here is real and unedited. Every number on these pages is generated automatically by the live system and published as it is: losses, mistakes and bad days included. Nothing is selected, smoothed, back-filled or hidden, and nothing is changed by hand to make it look better. The money is simulated (paper trading); the market data, the news and the AI agents' decisions are real. This is a personal research project, not a trading service, and nothing here is investment advice.
Live · 14 trading days
A simulated trading firm run by AI agents: researchers, long and short traders, options traders, a risk manager and a portfolio manager. Every desk is measured against a random desk that trades just as often, and challengers compete for each seat every three weeks.
Research · live paper test
A dip-buying strategy for large US stocks, built on point-in-time data and an event-driven backtester and tested against random picks. It beat the index on a risk-adjusted basis in its held-out test, then failed an older, untouched one. Both results are shown.