Comparative Analysis of Batch and Online Machine Learning Techniques for Fraud Detection: A Case Study on Real European Credit Card Transactions

Srinivasan, Saran Raj (2023) Comparative Analysis of Batch and Online Machine Learning Techniques for Fraud Detection: A Case Study on Real European Credit Card Transactions. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Machine learning has always played a important role in fraud detection, with different methods developing to meet the constantly changing strategies of the fraudsters. In the context of ”credit card fraud detection” this study, addresses the difficulties caused by missing data and class imbalance as well as comparing and analysing the performance of batch and online machine learning algorithms. The study utilizes the data set from Vesta Corporation managed by the IEEE Computational Intelligence Society from Europe, which contains real credit card transactions and is marked by a high level of class imbalance and 41percentage missing values. These missing values are handled using multiple imputation, and the imbalance is addressed using a hybrid method that combines SMOTE and random under sampling. The results demonstrate that online machine learning techniques, particularly Online Random Forest and Online XGBoost, outperform their batch methods. The study concludes that online machine learning models are more effective in handling imbalanced data sets with missing values and recommends further research to validate these findings on other data sets and domains.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Cosgrave, Noel UNSPECIFIED
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 > Credit. Debt. Loans. Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	23 May 2025 12:41
Last Modified:	23 May 2025 12:41
URI:	https://norma.ncirl.ie/id/eprint/7621

Actions (login required)

View Item