Overfitting — what it is and how to use it in trading
Definition
Overfitting is when a strategy's parameters are tuned so precisely to one specific stretch of historical data that they capture that stretch's random quirks rather than a durable market pattern.
How it works in the builder
An overfit strategy typically shows a great result on in-sample data (the data used to tune its parameters) and a noticeably weaker one on out-of-sample data it never saw during tuning. The gap between IS and OOS is the main tell.
Typical use
Checked via out-of-sample testing and walk-forward: if the result drops sharply on unseen data, or holds up only for one narrow set of parameters with no neighboring stable plateau, the strategy is likely overfit.
Common pitfalls
Even honest methodology can't fully rule out overfitting risk — the market can change structurally even after a stable walk-forward result. The more parameters a strategy has and the shorter the history, the higher the risk of fitting the past.
This block is available in the strategy builder
137 no-code blocks — build an entry condition with this term and test it on history
Historical results do not guarantee future ones. The service is an informational and analytical tool, not an individual investment recommendation; trades are not executed.