I built an overnight strategy tournament to find the best trading algorithm while I sleep

I built TradeSight — a self-hosted Python platform for algorithmic paper trading that runs overnight strategy tournaments to evolve the best-performing configuration before market open. Here's the part that actually surprised me: letting strategies compete and reproduce overnight produced a Sharpe ratio of 2.53 — vs 0.3–0.8 from static indicator configs I'd hardcoded. The tournament idea Most algo trading tutorials give you a fixed strategy: buy when RSI < 30, sell when RSI > 70. The problem is that works until it doesn't — markets shift, and static params go stale. So instead of tuning a single strategy, TradeSight runs a tournament each night : Seed ~20 strategy variants with randomized indicator weights (RSI threshold, MACD fast/slow, Bollinger width, etc.) Backtest each on the past 90 days of data Score by Sharpe ratio (risk-adjusted return) Keep the top 50%, mutate their params, repeat for 10 generations Promote the winner to live paper trading at market open This is basically a g