Fraud Detection Using Machine Learning Methods
Student
Sheng Huang
Advisor
Daniel Boley
Abstract
Credit card fraud detection is presently the most frequently occurring problem in the world. This is due to the rise in both online transactions and e-commerce platforms. This project aims to focus on machine learning algorithms to predict fraud transactions on the IEEE-CIS Fraud Detection dataset. The dataset is highly imbalanced and we proposed three sampling methods to address it. The algorithms are logistic regression, random forest, decision tree and support vector machine(SVM). The results of the algorithms applied on the three sampling datasets are evaluated by accuracy, AUC,precision, recall and F1-score.