Predicting Credit Card Fraud Using Conditional Generative Adversarial Network

Duggal, Purnima (2022) Predicting Credit Card Fraud Using Conditional Generative Adversarial Network. Masters thesis, Dublin, National College of Ireland.

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

Abstract

As the financial sector continues to flourish over these years, there have been significant changes in many conventional systems. One of them is carrying money in hand. Credit cards and debit cards have completely replaced carrying money in hand as the predominant method of payment. Numerous studies indicate that the use of credit cards vastly increased after the pandemic period. The increasing use of credit cards is a common target for cybercriminals and fraudsters. Although numerous steps have been taken to prevent credit card fraud, the problem still exists. The skewness or imbalance of the dataset is the most frequent problem that researchers encounter when conducting analysis using various machine learning models. In this research, I have addressed the problem of skewness of the dataset by using two approaches: SMOTE Technique and an unsupervised machine learning technique that is CT-GAN (Conditional Generative Adversarial Network). We used AUPRC as a performance indicator for both approaches. Three classifier models namely: Isolation Forest, Multi-Layer Perceptron and Random Forest are used to perform the experiments. We discovered that GAN performs well on two out of three models after analyzing both approaches and Isolation Forest outperforms the other two models, correctly detecting 86 % of credit card fraud.

Item Type:	Thesis (Masters)
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 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:	24 Jan 2023 12:51
Last Modified:	03 Mar 2023 12:59
URI:	https://norma.ncirl.ie/id/eprint/6114

Actions (login required)

View Item