NORMA eResearch @NCI Library

Safeguarding Financial Transactions: A Machine Learning Perspective on online payment network security

Yesudas, Shiron Shine (2024) Safeguarding Financial Transactions: A Machine Learning Perspective on online payment network security. Masters thesis, Dublin, National College of Ireland.

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

Abstract

The objective of this study is to describe the development of an advanced Intrusion Detection System (IDS) specifically meant for securing online payment transactions. The proposed work seeks to employ the most advanced modern machine learning techniques and comprehensively analyze threats. This system is aimed at real-time intrusion detection and prevention. In that regard, we will collect a lot of information using CICIDS2017 dataset and thereafter apply different machine learning algorithms such as Support Vector Classifier (SVC), Convolutional Gated Recurrent Unit (CGRU), Artificial Neural Network (ANN) for fraud detection. Furthermore, the suggestion has in mind making it user-friendly so that people can use it without any glitches. The overall goal of this system is improved security in online payments through AI-based intrusion detection which helps in mitigating risks and countering fraudulent activities. This research assesses three various machine learning techniques on their efficiency to detect fraudulent transactions. CGRU had the highest accuracy rate among them all with almost perfect 99.61%. SVC and ANN recorded slightly lower levels of accuracy at 94.59% and 97.97% respectively as compared to CGRU’s calculations accuracy rate value, thus implying its superior performance in accurately detecting fraudulent deals than others put together for analysis purposes or considerations made by these algorithms. These two findings underscore the importance of complex machine learning approaches to ensure reliability and security in digital financial transactions by providing a strong defense against frauds too.

Item Type: Thesis (Masters)
Supervisors:
Name
Email
Pantridge, Michael
UNSPECIFIED
Uncontrolled Keywords: Machine Learning; Intrusion Detection System; Online Payment Transactions; Support Vector Classifier (SVC); Convolutional Gated Recurrent Unit (CGRU); Artificial Neural Network (ANN)
Subjects: H Social Sciences > HG Finance
Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software > Computer Security
T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Ciara O'Brien
Date Deposited: 05 Jun 2025 11:16
Last Modified: 05 Jun 2025 11:16
URI: https://norma.ncirl.ie/id/eprint/7754

Actions (login required)

View Item View Item