loan-default

Predicting loan defaults using machine learning and hybrid feature engineering approaches.

End-to-end analysis of bank loan default risk using historical lending data to identify key risk factors, assess borrower behavior, and support data-driven credit decisions.

Uni-variate and Bi-variate analysis to understand the driving factor behind loan default

Loan-portfolio default analysis on 400 messy bank records: pandas cleaning pipeline (10 stages, 51 unit tests), feature engineering, scikit-learn logistic regression (AUC 0.617), risk-tier segmentation, and a Power BI dashboard spec with DAX measures and a 3-page layout.

Predicting loan default risk using Logistic Regression and CatBoost with business cost-based threshold optimization. Minimizes total financial loss by tuning decision thresholds using a cost-benefit matrix. Built with Python, CatBoost & Scikit-learn.

EDA and hypothesis testing project to identify key factors in loan default analysis

Production-ready Loan Default Prediction using LightGBM, Feature Engineering, Cross-Validation and Explainable AI (SHAP).

SQL credit risk analysis project focused on default rates, loan grades, borrower profiles, and data quality checks.

Loan Default Predictor on Lending Club dataset

End-to-end loan default risk analysis project using Python, SQL, Power BI, and Machine Learning to identify high-risk borrowers, predict default probability, and support credit-risk decision-making.

Two-model ML pipeline predicting loan defaults & loss severity using Random Forest + XGBoost in R | MAE: 5.2261 | Recall: 60.95%

A machine learning–based credit risk prediction system using XGBoost, deployed as an interactive Streamlit web application to classify applicants as Good or Bad credit risk.

Logistic Regression model predicting loan repayment vs default using financial attributes. Strong ROC-AUC (0.91) with business interpretability.

Análise exploratória de risco de crédito utilizando dados de empréstimos, com foco em inadimplência (default). O projeto investiga como variáveis financeiras como score de crédito, renda e Debt-to-Income Ratio influenciam a probabilidade de default, reproduzindo análises utilizadas por instituições financeiras.

Machine learning project for predicting loan default risk using borrower data, helping financial institutions make data-driven lending decisions.

SQL Server project analyzing a bank loan portfolio for default risk.

Distribution-shift-aware loan default prediction — adversarial validation revealed 91.5% train/test separation, guiding a LightGBM/CatBoost/XGBoost ensemble across 50+ Modal cloud experiments. Deep Learning IndabaX Zimbabwe 2026. Public LB 0.6840.

End-to-end MLOps pipeline for loan default prediction — 4 models tracked with MLflow, GradientBoosting champion at AUC 0.868 / PR-AUC 0.397 on 7% imbalanced data, alias-based model registry, and a FastAPI REST endpoint with Pydantic validation.

Production-ready machine learning pipeline for loan repayment prediction using CatBoost with cross-validation and model evaluation.