Use of Artificial Intelligence in cybersecurity threat detection in E-commerce and retail

Bhogle, Anuj Shashikant (2025) Use of Artificial Intelligence in cybersecurity threat detection in E-commerce and retail. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (364kB) | Preview

Abstract

The sphere of cybersecurity problems in e-commerce and retail keeps expanding in terms of size and complexity due to such factors as a constantly increasing number of online transactions, the blistering rate of the implementation of digital payment systems, and the changing modes and methods of attackers. Since it is becoming increasingly important that organizations have secure digital ecosystems, as a result of the trust needs of consumers and the need of maintaining financial integrity, there is an urgent need that organizations demand sophisticated state-of-the-art techniques to identify and eliminate fraudulent practices. This project study is about using Artificial Intelligence (AI), in particular, supervised machine learning approach, to detect cybersecurity threats within e-commerce space, in case of, transaction fraud. Using a real data set in which e-commerce transactions data had been anonymized, a Light Gradient Boosting Machine (LightGBM) model was trained and intensively optimized to identify fraudulent behavior accurately but minimally in false positive bets.

This report adds to the already existing body of research on AI-driven cybersecurity through a scalable and interpretable fraud detection pipeline that can be used in practice in retail settings. Besides, the resilience to new threats is emphasized in the study through the need to explain the black box of AI, the quality of the data used in providing resilience, and the retraining of models that help to build resilience of the emerging threats. It suggests the need to investigate the application of unsupervised learning, ensemble stacking, or multi-modal data combination to cover more detection and system resilience.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Zahoor, Sheresh UNSPECIFIED
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security H Social Sciences > HF Commerce > Electronic Commerce H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Retail Industry
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	12 Aug 2026 08:33
Last Modified:	12 Aug 2026 08:33
URI:	https://norma.ncirl.ie/id/eprint/9500

Actions (login required)

View Item