Bibliometric Analysis of Recent Trends in Machine Learning for Online Credit Card Fraud Detection

Abstract

Online credit card fraud (OCCF) is the malicious act of using credit card details belonging to another person to complete fraudulent transactions over the Internet. Naturally, masses of researchers have engaged in the imperative search for effective solutions across a wide range of disciplines. The result is a rich tapestry of methodologies, models, frameworks, and inventions exhibiting dramatic spread and growth. However, this also results in an unorganized research domain. In this state, a bibliometric analysis is a useful technique for establishing a reconciled snapshot of the OCCF research domain. This paper has particular interest in determining the intellectual structure of the knowledge of machine learning, deep learning, and ensemble learning models for early detection of OCCF. This bibliometric analysis is conducted using 524 publications between 2013 and 2022 extracted from the SCOPUS core collection database. Microsoft Excel, VOSViewer, and Biblioshiny software tools were used for data analysis. The findings indicate that ensemble learning models are trending and the three most authoritative authors have been exposed in this study. There is a sharp rise in global publications annually and India has the most publications with the most impactful authors. Five broad clusters of knowledge are imbalanced data, anomaly detection, machine learning, decision trees, and ensemble learning. Intellectual collaboration across regions is strong amongst Asia, Europe, and North America with weak associations between Africa and South America. This is the first bibliometric analysis in the domain of OCCF detection to the best of the author’s ability. The findings significantly contribute to the application of OCCF detection through the creation of intellectual patterns in existing literature. The results bring about synthesis within a domain of research that is currently disorganized. This in turn helps researchers to identify research gaps, and areas for further research and formulate a curriculum.