Feature Selection and Machine Learning Algorithms for an Improved Credit Card Fraud Detection System

Omoworare, Boluwatife Joseph (2021) Feature Selection and Machine Learning Algorithms for an Improved Credit Card Fraud Detection System. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (969kB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Our world today is characterised by the fast adoption of technology in everyday living. This is evident in the rise of e-commerce, online shopping, online gaming, e-learning, online payment systems, e-banking, etc. Therefore, it has become imperative that more research be conducted to investigate and develop more efficient and effective fraud detection systems. Several researches have leveraged the use of machine learning algorithms and complex data mining methodologies to produce efficient fraud detection systems. Hence, this paper implemented different machine learning fraud detection models with and without feature selection to ascertain if using feature selection improved the accuracy of the models. Therefore, correlation matrix was selected as the feature selection technique which was used against random forest and logistic regression. The dataset used was a synthetic dataset created by a researcher in the IBM TJ Watson Research Centre to address the lack of labelled datasets for credit card fraud detection. After implementation and evaluation, results showed that the Random Forest classifier with feature selection achieved the highest accuracy of 98%. Thus, showing that feature selection improved the accuracy of the models.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	credit card fraud; feature selection; machine learning
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 > HF Commerce > Electronic Commerce 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:	27 Feb 2023 15:43
Last Modified:	02 Mar 2023 08:21
URI:	https://norma.ncirl.ie/id/eprint/6244

Actions (login required)

View Item