Some guy built a complete AI-driven hedge fund, from Asindu Drileba
Here is the original thread.
All of the agents show their reasoning so you can see how they work.
1 • Market Data Agent: gathers market data like stock prices, fundamentals, etc.
2 • Quant Agent: calculates signals like MACD, RSI, Bollinger Bands, etc.
3 • Fundamentals Agent: analyzes profitability, growth, financial health, and valuation.
4 • Sentiment Agent: looks at insider trades to determine insider sentiment.
5 • Risk Manager: determines risk metrics like volatility, drawdown, and more.
6 • Portfolio Manager: makes final trading decisions and generates orders.
Here is the GitHub repository.
Why would this work or be good at? Why would it not work? I don't think it will work since the same model will be used my many if successful and the gains will be cancelled out.
Larry Williams comments:
Ultimate curve fit - wait a year to know.
Hernan Avella writes:
This is absolutely the way to go, but there’s a bit more to what we get to call “Agent”. Also his quant module is looking at dumb shit.
Julian Rowberry responds:
horses had a good track record before cars. AI is making key opinion leaders redundant too.