# Multi-model analysis

> Multi-model analysis - Use Python functions to aggregate DataRobot model insights into
> visualizations.

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 `2026-05-06T18:17:09.585447+00:00` (UTC).

## Primary page

- [Multi-model analysis](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/time-series/ml-analysis.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.
- [Time series and specific use cases](https://docs.datarobot.com/en/docs/api/dev-learning/accelerators/time-series/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/multi_model_analysis/Multi-Model%20Analysis.ipynb)

DataRobot is designed to help you experiment with different modeling approaches, data preparation techniques, and problem framings. You can iterate fast with a tight feedback loop to quickly arrive at the best approach.

Sometimes you may wish to break your use case into multiple models, likely across multiple DataRobot projects. Maybe you want to build a separate model for each country or one for different periods of the year. In this case, it helps to bring all of your model performances and insights into one chart.

This accelerator shares several Python functions that can take the DataRobot insights—specifically model error, feature effects (partial dependence), and feature importance (SHAP or permutation-based) and bring them together into one chart, allowing you to understand all of your models in one place and more easily share your findings with stakeholders.