Organizations by tags - shap: Companies and research groups using SHAP for model explainability, feature attribution, and production ML
Discover organizations tagged with shap that employ SHAP (SHapley Additive exPlanations) for model interpretability, feature attribution, and responsible AI across finance, healthcare, adtech, and enterprise ML. This list surfaces real-world implementations of SHAP with XGBoost, LightGBM, CatBoost, scikit-learn, PyTorch, and TensorFlow models and highlights integration patterns for explainability pipelines, automated reporting, and model debugging. Use the filtering UI to narrow results by industry, model type, library, or open-source contribution, compare implementation patterns, and surface case studies, repositories, and production architectures that leverage SHAP values. Click an organization to view practical best practices, reproducible examples, and actionable steps to adopt SHAP-powered explainability in your ML stack.