In-sample
—
The best review sequence usually starts with stability and explanation, not with total return.
A modest win rate with strong payoff balance can be healthier than a flashy win rate that depends on one fragile trade pattern.
Two strategies can lose the same amount and feel completely different to run depending on streak length, recovery time, and concentration.
A system may still be healthy even after a weak phase if the market shifted outside its intended environment and the damage stayed within expected bounds.
Tune a strategy hard enough and it fits the past perfectly — then falls apart on new data. Push the tuning up and watch the out-of-sample curve diverge from the in-sample one.
Do not optimize to erase normal drawdown.