Thesis Abstract

Abstract
The rapid growth of e-commerce platforms has brought about the need for effective fraud detection systems to combat fraudulent activities. This thesis presents the development of a Machine Learning-based System for Fraud Detection in E-commerce Platforms. The primary objective of this research is to design and implement a system that can accurately detect and prevent various forms of fraud in online transactions. The study focuses on utilizing machine learning algorithms to analyze transaction data and identify suspicious patterns indicative of fraudulent behavior. The research begins with a comprehensive literature review in Chapter Two, which explores existing fraud detection techniques, machine learning algorithms, and their applications in e-commerce fraud detection. Chapter Three outlines the research methodology, detailing the data collection process, feature selection, model training, and evaluation metrics employed in the study. The methodology incorporates supervised learning techniques such as logistic regression, decision trees, and ensemble methods to build a robust fraud detection model. Chapter Four presents the detailed discussion of findings, including the performance evaluation of the developed fraud detection system. The results demonstrate the effectiveness of the machine learning model in accurately identifying fraudulent transactions while minimizing false positives. The chapter also discusses the implications of the findings and potential areas for further research and improvement. In conclusion, Chapter Five summarizes the key findings of the study and reflects on the significance of developing a machine learning-based fraud detection system for e-commerce platforms. The research contributes to the enhancement of fraud prevention mechanisms in online transactions, ultimately improving the trust and security of e-commerce environments. The study underscores the importance of leveraging advanced technologies such as machine learning to address evolving challenges in fraud detection and prevention. Overall, this thesis provides a comprehensive analysis of the development of a Machine Learning-based System for Fraud Detection in E-commerce Platforms, offering insights into the potential applications and benefits of utilizing machine learning techniques in combating fraud. The findings of this research have practical implications for e-commerce businesses seeking to enhance their security measures and protect both consumers and merchants from fraudulent activities in online transactions.

Thesis Overview