SHAP
Observability
Overview
SHAP (SHapley Additive exPlanations) is an open-source library that provides a unified approach to explaining model predictions using game theory. It computes Shapley values to attribute the contribution of each feature to individual predictions. SHAP supports tree-based models, deep learning, and general ML models, and provides global and local interpretability for model explainability and fairness.
- Pricing model
- Free
- Deployment
- Self-hosted / on-premises, API / SDK
- Regions served
- Global
- Categories
- Free, Software & technology, Workflow orchestration, Observability, API / SDK, Self-hosted / on-premises, Predictive / classical ML, Functional application
- Last updated
- 2 October 2026
- Published
- 2 October 2026
Use cases
Deployment options
Data sources & provenance
Where this information came from, how it was checked and when it was last looked at. “Last updated” records a change to the record — it does not mean the record was verified.
- Data quality
- Data quality: Editorially Reviewed
- Primary source
- shap.readthedocs.io
- Sources cited
- 2
- Last reviewed
- 28 September 2026
- Last updated
- 2 October 2026
Spotted something out of date?
Anyone can suggest a correction — you don't need an account. An editor checks every suggestion against the sources before the record changes.