yramon

edc

Heuristic best-first algorithm for computing Evidence Counterfactuals (SEDC): explaining the model predictions of any classifier using a minimal set of features, such that removing these features results in a predicted class change.

LimeCounterfactual

Hybrid algorithm based on SEDC and LIME for computing Evidence Counterfactuals (LIME-Counterfactual): explaining the model predictions of any classifier using a minimal set of features, such that removing these features results in a predicted class change.

ShapCounterfactual

Hybrid algorithm based on SEDC and SHAP for computing Evidence Counterfactuals (SHAP-Counterfactual): explaining the model predictions of any classifier using a minimal set of features, such that removing these features results in a predicted class change.

yramon.github.io

yramon/edc

Heuristic best-first algorithm for computing Evidence Counterfactuals (SEDC): explaining the model predictions of any classifier using a minimal set of features, such that removing these features results in a predicted class change.

yramon/LimeCounterfactual

Hybrid algorithm based on SEDC and LIME for computing Evidence Counterfactuals (LIME-Counterfactual): explaining the model predictions of any classifier using a minimal set of features, such that removing these features results in a predicted class change.

yramon/ShapCounterfactual

Hybrid algorithm based on SEDC and SHAP for computing Evidence Counterfactuals (SHAP-Counterfactual): explaining the model predictions of any classifier using a minimal set of features, such that removing these features results in a predicted class change.

yramon/yramon.github.io