# Robust feature selection

> Robust feature selection - This accelerator introduces an approach to select robust features, use
> multiple seeds for cross validation, add dummy features to compute the median permutation
> importance, and then select the most robust dummy features.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-05-06T18:17:09.572271+00:00` (UTC).

## Primary page

- [Robust feature selection](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/adv-analytics-tools/rob-fi.html): Full documentation for this topic (HTML).

## Related documentation

- [Developer documentation](https://docs.datarobot.com/en/docs/api/index.html): Linked from this page.
- [Developer learning](https://docs.datarobot.com/en/docs/api/dev-learning/index.html): Linked from this page.
- [AI accelerators](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/index.html): Linked from this page.
- [Advanced analytics and tools](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/adv-analytics-tools/index.html): Linked from this page.

## Documentation content

[Access this AI accelerator on GitHub](https://github.com/datarobot-community/ai-accelerators/blob/main/advanced_ml_and_api_approaches/Robust_Feature_Impact/Robust_Feature_Impact.ipynb)

Machine learning models have biases using small data, and some industries (e.g., healthcare and manufacturing) lack labeled data. In light of this, a good approach is to select robust features to build models. This accelerator introduces an approach to select robust features, use multiple seeds for cross validation, add dummy features to compute the median permutation importance, and select the most robust dummy features.

This notebook outlines how to:

- Connect to DataRobot.
- Create multiple projects by multiple seeds and add dummy features.
- Create blender models of top-performing models.
- Retrieve modeling permutation importance from the top-performing blender models.
- Remove features whose permutation importance is lower than dummy features.