Every trading bot post ends the same way: a green equity curve and a suspicious silence about whether it made real money. This post is the other one. I spent months building an algorithmic trading system, tested it as honestly as I know how, and here is the headline result:
My best strategy returned +4.33% over three years of out-of-sample testing. Buying Bitcoin once and holding it returned +127.77%.
I'm publishing that number instead of hiding it, because getting to a number I couldn't argue with turned out to be the entire project.
What I built
TradingAI is about 4,000 lines of Python: a strategy engine, a backtester, a walk-forward validation harness, a live paper-trading bot with Telegram alerts, a real-time dashboard, and 130+ tests running in CI. The bot trades a simple, transparent rule (a Donchian channel breakout: buy 20-day highs, exit on a trailing stop) on real exchange data via ccxt.
