> ## Documentation Index
> Fetch the complete documentation index at: https://docs.trinigence.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Overfitting & Guardrails

> How strategies become overfit and how to protect against it.

## What overfitting looks like

Overfitting happens when a strategy **matches noise instead of signal**. It looks great on a specific slice of history, but collapses elsewhere.

Common warning signs:

* extreme results on short ranges
* performance collapses out of sample
* tiny parameter changes break the strategy
* the logic becomes complex without a clear reason

***

## Why it happens

Overfitting is usually caused by:

* too many degrees of freedom (filters, conditions, parameters)
* too little data for the number of choices
* repeated tweaking until results look good
* optimizing to a single market regime

***

## Guardrails that actually help

Use these to keep strategies realistic:

* **Reduce complexity** before optimizing. Fewer moving parts = fewer false positives.
* **Test across ranges and regimes**, not just one period.
* **Prefer logic changes over parameter tweaks** when behavior is wrong.
* **Require stability**, not peak performance. Consistent results beat a single perfect run.
* **Compare to a baseline** so you know what really improved.

<Info>
  A strategy that is slightly worse but stable is usually better than a perfect, fragile one.
</Info>

***

## What to read next

<CardGroup cols={2}>
  <Card title="Parameter ranges" icon="sliders" href="/iteration-optimization/parameter-ranges" />

  <Card title="When not to optimize" icon="ban" href="/iteration-optimization/when-not-to-optimize" />

  <Card title="How to read results" icon="magnifying-glass-chart" href="/backtesting/how-to-read-results" />

  <Card title="Common pitfalls" icon="triangle-exclamation" href="/backtesting/common-pitfalls" />
</CardGroup>