Stochastic 20/80 1h

On data it never saw, the agent averaged -11.1bp per trade after costs (win rate 48.2% — irrelevant when losers outweigh winners).

Try: This is an entry-signal problem, not a tuning problem. Change the core idea: different condition, different timeframe, or add a regime filter (e.g. only trade high-volatility periods) — don't just widen stops.

It loses on BTC/USDT:USDT, ETH/USDT:USDT, SOL/USDT:USDT — under 60% of its universe is positive, which usually means the backtest found luck, not a mechanism.

Try: Either the thesis only applies to certain assets (then say so — trim the universe to where the mechanism makes sense), or the signal is noise. Ask: WHY would this work on some symbols and not others?

Simulated at responsible sizing, the worst drawdown hits 92% — deep enough that most people abandon the strategy exactly at the bottom.

Try: Cut risk per trade, tighten the catastrophe stop, or reduce concurrent positions. An edge you can't hold through its drawdown is an edge you don't have.