explainable-machine-learning

This paper presents an explainable machine learning framework using SHAP analysis to predict and profile broadband adoption disparities at the census-tract level in the United States, identifying key factors like income and education for policy targeting.

This paper introduces a statistically grounded framework using Bernoulli Naïve Bayes and χ²-guided binarization for interpretable clinical classification, achieving competitive AUC scores on benchmark datasets while providing explicit decision rules and calibrated risk estimates.