Explainable Boosted Scoring with Python: turning XGBoost, LightGBM, and CatBoost into explainable scorecards

An AI-driven credit risk management platform using alternative data, psychometrics, and explainable ML to expand financial inclusion.

This is a machine learning project for credit decisioning for banks or other financial institutions and in this project, we will use machine learning models for classification.

📊 Predict loan defaults reliably using a hybrid ensemble of machine learning models for enhanced accuracy and real-time insights in credit risk assessment.

Built and deployed a Flask-based machine learning system to predict loan default risk using customer demographics and financial indicators. Applied advanced ensemble models like XGBoost and LightGBM to achieve ~99% accuracy. Designed a full-stack solution with real-time prediction capabilities, enabling faster, smarter loan decisions in banking.

A full-stack machine learning application that predicts loan approval and credit risk percentage using the Home Credit Default Risk dataset. It integrates a trained classification model with a Flask API and React frontend to provide real-time risk evaluation based on applicant financial and external credit bureau data.

This project implements a production-style machine learning pipeline to predict loan approval decisions based on applicant financial and demographic data. The goal is to simulate a real-world credit risk assessment system, enabling financial institutions to identify high-risk applicants and minimize potential losses.

Explainable credit risk modeling on the Home Credit dataset with LightGBM/CatBoost, SHAP/LIME, Ollama-based reporting, and API deployment.

End-to-end credit risk modeling and loan default prediction using LendingClub data

🏦 Assess credit risk and predict loan defaults with this machine learning model and interactive Streamlit dashboard for financial institutions.