Credit Card Fraud Detection using Ensemble Learning Algorithms

Figuerola Ullastres, Eva (2022) Credit Card Fraud Detection using Ensemble Learning Algorithms. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (8MB) | Preview

Abstract

Credit card fraud is a type of financial crime where fraudsters use people's credit card details to purchase goods and services without the permission of the card- holder. The volume of online transactions has grown substantially in recent years, which has led to an increase in fraud attempts. Businesses lose billions due to fraud every year. Since only a small percentage of credit card transactions are fraudulent, fraud datasets are highly imbalanced, making fraud detection a challenging task. Machine learning plays an important role in credit card fraud detection. This study examines the performance of tree-based ensemble methods in detecting fraudulent transactions. Different classifiers; Random Forest, Bagging, XGBoost, LightGBM and CatBoost are implemented in this research. A hybrid sampling approach of random undersampling (RUS) and Borderline-SMOTE is used to handle the class imbalance. The results indicate that boosting classifiers outperformed bagging classifiers in detecting fraud. XGBoost and LightGBM achieved the best performance in terms of F1 Score (0.70), Matthews Correlation Coefficient (MCC) (0.71) and Area Under the Precision-Recall Curve (AUC-PR) (0.73).

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Credit Card Fraud; Machine Learning; Class Imbalance; Ensemble Methods; XGBoost; LightGBM; RUS; BorderlineSMOTE
Subjects:	H Social Sciences > HV Social pathology. Social and public welfare > Criminology > Crimes and Offences Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HG Finance > Banking Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	24 Jan 2023 15:10
Last Modified:	03 Mar 2023 12:20
URI:	https://norma.ncirl.ie/id/eprint/6119

Actions (login required)

View Item