Backtesting Myths That Quietly Wreck Trading Bots

Overfitting is the most common failure mode: a strategy tuned so precisely to historical data that it has effectively memorized the past rather than learned a repeatable edge.

Slippage and fees are the second-most-ignored variable. A strategy that looks profitable with zero-cost assumptions can flip negative the moment realistic spreads and commissions are applied.

Before trusting a backtest, run it across multiple, non-overlapping market regimes — trending, ranging, and high-volatility periods — and apply conservative slippage assumptions throughout.