Machine Learning Research

Predicting Fraudulent Transactions: A Comparative Study

This project compared several machine learning approaches for fraudulent transaction prediction on a dataset with more than 6.3 million rows. The work included preprocessing, feature selection, and evaluation across logistic regression, random forest, XGBoost, stacking, and CNN models.

Download PDF Back to Projects

Highlights

Key signals from the work.

Compared logistic regression, decision tree, random forest, XGBoost, stacking, and CNN approaches on the same fraud-detection task.

Built a preprocessing workflow with duplicate removal, one-hot encoding, class-ratio adjustment, and recursive feature elimination.

Evaluated models with accuracy, precision, recall, and confusion matrices to make the comparison more rigorous and interpretable.

Tools and Focus Areas

Pythonpandasscikit-learnTensorFlowXGBoost

Contact