This paper presents a systematic literature review on e-commerce fraud detection using machine learning and data mining techniques. The rapid growth of e-commerce, accelerated by the COVID-19 pandemic, has led to a significant increase in digital fraud and associated losses. To address this issue, the study employs the PRISMA methodology to analyze 101 publications, identifying research gaps, trends, and future directions in the application of machine learning and data mining techniques for fraud detection in e-commerce platforms. The review highlights the increasing use of artificial neural networks in fraud detection and identifies key techniques such as decision trees, random forests, and logistic regression. The study also identifies common vulnerabilities in e-commerce platforms, including certificate duplicity, unsecure protocols, and unsecure databases, and discusses common fraud types such as financial fraud, web application fraud, spam/phishing fraud, triangulation fraud, and bot fraud. The review finds that credit card fraud is the most prevalent type of fraud, with a significant number of articles focusing on this area. The study also identifies research gaps, including the need for better handling of imbalanced data in fraud detection, and suggests future research directions in this area. The findings of this review provide insights for industry stakeholders on key machine learning and data mining techniques for combating e-commerce fraud.This paper presents a systematic literature review on e-commerce fraud detection using machine learning and data mining techniques. The rapid growth of e-commerce, accelerated by the COVID-19 pandemic, has led to a significant increase in digital fraud and associated losses. To address this issue, the study employs the PRISMA methodology to analyze 101 publications, identifying research gaps, trends, and future directions in the application of machine learning and data mining techniques for fraud detection in e-commerce platforms. The review highlights the increasing use of artificial neural networks in fraud detection and identifies key techniques such as decision trees, random forests, and logistic regression. The study also identifies common vulnerabilities in e-commerce platforms, including certificate duplicity, unsecure protocols, and unsecure databases, and discusses common fraud types such as financial fraud, web application fraud, spam/phishing fraud, triangulation fraud, and bot fraud. The review finds that credit card fraud is the most prevalent type of fraud, with a significant number of articles focusing on this area. The study also identifies research gaps, including the need for better handling of imbalanced data in fraud detection, and suggests future research directions in this area. The findings of this review provide insights for industry stakeholders on key machine learning and data mining techniques for combating e-commerce fraud.