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

# Explainability

Explainability tools in our platform provide in-depth insights into how individual features drive model predictions, offering both **global** and **local** perspectives on feature importance and impact. By leveraging SHAP values, users can [analyze feature influence](/ax/machine-learning/machine-learning/how-to-ml/explainability/interpreting-and-analyzing-feature-importance-values) across all predictions to identify high-impact features globally, as well as drill down into local explainability for specific instances. These insights help model owners interpret model behavior, diagnose issues such as drift or performance drops, and understand cohort-specific dynamics that may require tailored model adjustments. With explainability, users can maintain transparency, enhance model trustworthiness, and take proactive steps to refine model performance and fairness.

## Explainability Tutorials

Examples for logging explainability metrics. Click [here](/ax/machine-learning/machine-learning/how-to-ml/explainability/explainability) for more information on how to log feature importance and use explainability.

|                                      |                                                                                                                                                                      |
| ------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| SHAP: Guide to Getting Started       | [Colab Link](https://colab.research.google.com/github/Arize-ai/tutorials_python/blob/main/Arize_Tutorials/SHAP/SHAP_Tutorial_Base_Version.ipynb)                     |
| SHAP: Neural Network on Tabular Data | [Colab Link](https://colab.research.google.com/github/Arize-ai/tutorials_python/blob/main/Arize_Tutorials/SHAP/SHAP_Values_For_Neural_Network_on_Tabular_Data.ipynb) |
| Surrogate Model Explainability       | [Colab Link](https://colab.research.google.com/github/Arize-ai/tutorials_python/blob/main/Arize_Tutorials/SHAP/Surrogate_Model_Feature_Importance.ipynb)             |
| One Hot Encoding Decomposition       | [Colab Link](https://colab.research.google.com/github/Arize-ai/tutorials_python/blob/main/Arize_Tutorials/SHAP/Example_One_Hot_Encoding_Shap_Decomposition.ipynb)    |

## Explainability Approaches

Arize supports 2 methods for ingesting and visualizing feature importance

<CardGroup>
  <Card title="Method" img="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/f430f18f-image.jpeg" href="/ax/machine-learning/machine-learning/how-to-ml/explainability/shap">
    User Calculated SHAP
  </Card>

  <Card title="Method" img="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-docs-images/171e0488-image.jpeg" href="/ax/machine-learning/machine-learning/how-to-ml/explainability/surrogate-model">
    Surrogate Model
  </Card>
</CardGroup>