Predicting loan defaults using Random Forest with SMOTE, SHAP, LIME, and fairness evaluation via AIF360 and Fairlearn

An AI-powered bridge health classification system that automatically categorizes bridge inspection reports into health levels using machine learning. The system leverages Explainable Boosting Machine (EBM) to achieve high accuracy while maintaining interpretability.

This repository implements an Explainable Boosting Machine (EBM) model for breast cancer classification using scikit-learn and interpret. The project includes data preprocessing, model training, accuracy evaluation, and feature importance visualization.

This project applies Microsoft's InterpretML library to analyze Titanic survival data using two ML models: the Explainable Boosting Machine (EBM), a fully transparent glassbox model, and Random Forest, a blackbox model. The EBM allows each prediction to be traced back to specific features such as gender, age, and passenger class.