Method evidence record

SHAP

SHAP is a model-explanation method, introduced by Scott Lundberg and Su-In Lee in 2017, that uses Shapley values from cooperative game theory to measure how much each feature contributes to an individual prediction, making the output of black-box machine-learning models interpretable. It supports both global explanations (overall feature importance) and local explanations (why one specific prediction came out the way it did).

Sources recorded, not reviewed

Source record

Citations copied verbatim from the method’s source record. No claim-level verification is inferred from them.

SHAP (SHapley Additive exPlanations)

Taxonomic method record · ml-model / machine-learning

Lundberg, S.M. & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems, 30, 4766–4777. · URL

Open full method

Curated claims

Claims persisted in the evidence ledger, each with its own assessment.

No curated claims yet

This view does not invent a claim assessment when the ledger has none.

Related methods

Generated from the method graph and shown as machine-suggested relations — no evidence claim is inferred.

Same method familyDecision Treemachine-suggested · Relational suggestion, not evidence.Same method familyGaussian Mixture Modelmachine-suggested · Relational suggestion, not evidence.See alsoLogistic Regressionmachine-suggested · Relational suggestion, not evidence.Same method familyRandom Forestmachine-suggested · Relational suggestion, not evidence.Same method familyXGBoostmachine-suggested · Relational suggestion, not evidence.