/trade/backtest runs five pre-built strategies — MA(50/200) crossover, RSI(14) mean-reversion, Bollinger reversion, MACD crossover, Donchian breakout — against real historical bars over a 2-to-10-year window you choose. Backtesting is the most-misused tool in quantitative analysis: when done correctly, it reveals real edges; when done incorrectly, it manufactures false confidence in strategies that will fail in production. The discipline matters more than the technology.

A backtest runs a strategy through historical data to estimate how it would have performed in the past. The output is typically: cumulative returns, Sharpe ratio, max drawdown, win rate, average win vs. average loss.

The implicit assumption — that historical performance is informative about future performance — is true ONLY when the backtest methodology is rigorous. Most amateur backtests violate one or more methodological requirements and produce wildly optimistic results that don't survive contact with live trading.