What is Out-of-Sample Data?

Out-of-sample data is history that the strategy was not built or tuned on, held back to test it more fairly. You design the rules on in-sample data, then check them on out-of-sample data that the rules have never seen. A strategy that holds up out-of-sample is more believable than one that only shines in-sample.

Why Out-of-Sample Data matters

It is the closest a backtest gets to an honest dress rehearsal before live conditions.

Related terms

Lessons that use this term

Continue