Explainable AI
SHAP
SHAP (SHapley Additive exPlanations) is a game theoretic approach for explaining the output of any machine learning model.
SHAP (SHapley Additive exPlanations) is a game theoretic approach. SHAP considers marginal contribution for every feature, to explain the output of any machine learning model. For a given sample data set, SHAP permutes the values for each feature, to see how much the particular feature is affecting your output, and that marginal contribution will be your estimation for that particular feature.
Liked the content? you'll love our emails!
Oops! Something went wrong while submitting the form.
See how AryaXAI improves
ML Observability
Learn how to bring transparency & suitability to your AI Solutions, Explore relevant use cases for your team, and Get pricing information for XAI products.
