This project explores explainability techniques on tabular data using linear regression, random forests and GAM. We apply XAI methods — including t-values interpretation, feature importance for random forests and SHAP as a post hoc method — to better understand model predictions and decision logic.
Due to data confidentiality constraints, the datasets used in this study are not publicly available in this repository.
Contents
- Data analysis
- Machine learning interpretation (linear regression, random forest and GAM)
- SHAP post hoc method