IEEE

Tabular Data Classification and Regression: XGBoost or Deep Learning With Retrieval-Augmented Generation

Abstract: Tabular data is the most prevalent form of structured data, necessitating robust models for classification and regression tasks. Traditional models like eXtreme Gradient Boosting (XGBoost) ...
GitHub

Project Title: Feature Engineering and Imbalanced Data in Money Laundering Detection: A Comparative Study of ML Algorithms

This project primarily used the small dataset with a high illicit ratio, which contains 5,078,345 financial transactions spanning 10 days.It effectively addresses challenges such as overlap and ...
IEEE

Comparative Analysis of Flood Risk Prediction Using ML Models: CART, SVM, and RF

Abstract: A key component of reducing the effects of floods and facilitating disaster preparedness is flood risk mapping. Three ML models—Classification and Regression Tree (CART), Random Forest (RF), ...