Technical details

Supported models

• Linear Regression, Logistic Regression

• Random Forest

• Decision Tree

• Gradient Boosting

• XGBoost

• Dense Neural Network

Supported explaination methods

• LIME

• Integrated Gradients

• Saliency

• DeepLift

• InputXGradient

• FeatureAblation

• ShapleyValueSampling

• KernelShap

Evaluation metrics

• Robustness: Sensitivity

• Faithfulness: Infidelity, Comprehensiveness, Sufficiency, Faithfulness Correlation, AUC-TP, Monotony

• Complexity: Complexity, Sparseness

More details can be found in this page.