A Comprehensive Review on Fraud Detection in E-Commerce Using Machine Learning and Big Data Analytics
Keywords:
Cybersecurity, Real-Time Transaction Monitoring, Anomaly Detection, Big Data Analytics, Machine Learning, E-commerce Fraud DetectionAbstract
Abstract—The enormous growth of e-commerce systems has increased the volume of online transactions by leaps and bounds, making them ripe for fraudulent activities such as payment fraud, identity theft, and account hijacking. Conventional rule-based fraud detection systems often miss complex and evolving fraud patterns and hence ought to give way to more advanced technologies. This paper that reviews literature focuses on the role of machine learning and big data analytics to bolster fraud detection mechanisms for e-commerce settings. Machine learning techniques, which consist mainly of supervised, unsupervised, and ensemble method types, have shown themselves to have exceptional capabilities in deducing unseen patterns and anomalies in large-scale transaction data. We observe that algorithms like Decision Trees, Random Forest, Support Vector Machines, and Deep Learning have been widely used to enhance the accuracy of anomaly detection, while the positivity of false detection was decreased. It is also observed that big data frameworks support processing really massive, high-velocity, and heterogeneous datasets in real time, making modern-day fraud detection both timely and efficient. Effecting a critical analysis of the literature of different schools, the paper reviews those issues absorbed by the literature, mainly methodologies, data sets, performance metrics, and the system architectures being used or suggested in relation to fraud detection systems. Along the way, it trots down infinitesimal challenges in the work of fraud detection systems, among them imbalance in the data present itself, scalability with model dependency, data privacy, and changing notions of fraud using the ease and security of worldwide connectivity and anonymity. The future orientations represented by federated learning, explainable artificial intelligence (XAI), and real-time analytics are also deliberated. Needless to say, this study will offer useful information in portraying the trend of advances, obstructions, and futures of dealing with e-commerce fraud detection and thus assist in indicative directions concerning future research for those stakeholders in academia or industry who cannot wait to see emerge the solid foundations for fraud-scrubbing services imbued with colossal scaling and intelligence.
References
O. Ipinnimo et al., “A machine learning-driven campus e-commerce system for fraud detection and financial sustainability in higher institutions,” Journal of Innovation Science and Technology, vol. 5, no. 1, 2026.
E. Evelyn and A. S. Paramita, “Machine learning-based fraud detection in e-commerce transactions,” International Journal of Informatics and Information Systems, vol. 9, no. 1, pp. 283–294, 2026.
K. G. Akintola et al., “Roles of big data analytics on customer experience in eCommerce and digital financial platforms,” Annals of Data Science, pp. 1–13, 2026.
F. Syed, R. Kalpana, and A. S. Subhiksh, “Optimizing e-commerce insights through synthetic data generation and big data-driven machine learning,” in Recent Advances in Computational Methods in Science and Technology, CRC Press, pp. 85–90, 2026.
K. K. Kondapalli, “Healthcare fraud at scale: Comparative analysis of ML architectures for insurance claims validation in big data environments,” QIT Press-International Journal of Computer Science and Engineering Research and Development, vol. 6, no. 1, pp. 8–25, 2026.
G. Kostopoulos et al., “Deep learning for e-Commerce: Recent developments in prediction, personalization and decision intelligence,” Applied Sciences, vol. 16, no. 5, p. 2263, 2026.
O. M. Olaniyi et al., “Conversational AI-powered fraud prevention in augmented reality e-commerce: A natural language processing framework for real-time transaction security,” Asian Journal of Research in Computer Science, vol. 19, no. 1, pp. 255–270, 2026.
T. Balaji, “AI-based big data observation method and process,” International Journal of Engineering Researches and Management Studies, vol. 13, no. 3, pp. 1–12, 2026.
G. S. Sindhu et al., “Scalable credit-card fraud detection using a RAAE and XGBoost,” in Proc. 2nd International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), IEEE, 2026.
V. Keerthan et al., “Explainable artificial intelligence in anomaly detection for threat management in e-commerce platform,” in Proc. International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA), Atlantis Press, 2026.
C. Lin et al., “Reinforcement learning of large language models for interpretable credit card fraud detection,” arXiv preprint arXiv:2601.05578, 2026.
S. V. Oprea and A. Bâra, “How are trends in explainable AI redefining e-commerce? From black boxes to transparent decisions through semantic analysis,” IEEE Access, 2026.
H. M. Jadah, S. Fatima, and N. H. M. Al-Husainy, “Detecting and preventing fraud in banks using artificial intelligence (AI): A literature review,” in AI-Driven Security for Next-Generation IoT Systems, pp. 191–205, 2026.
J. R. T. Wijaya, D. N. Rahmatika, and E. Herwiyanti, “Machine learning techniques in detecting fraud: A state of the art review in the Scopus database,” Jurnal Bina Akuntansi, vol. 13, no. 1, 2026.
L. Theodorakopoulos, A. Theodoropoulou, and C. Klavdianos, “Big data analytics and AI for consumer behavior in digital marketing: Applications, synthetic and dark data, and future directions,” Big Data and Cognitive Computing, vol. 10, no. 2, p. 46, 2026.
Z. Mohammadnazari and U. Farooq, “Machine learning and data analytics in the gig economy: Big data applications,” in Smart and Sustainable Gig Economy in the Industrial 5.0 Era, CRC Press, pp. 147–163, 2026.
K. A. Shakil et al., “Securing big data assets in a data-driven world with deep learning and natural language processing,” in Cybersecurity, Cybercrimes, and Smart Emerging Technologies, CRC Press, pp. 58–64, 2026.
E. Dritsas and M. Trigka, “Machine learning in e-commerce: Trends, applications, and future challenges,” IEEE Access, 2025.
K. R. Khanna et al., “Detecting fraud in e-commerce transactions through comprehensive user behavior and process analysis,” International Journal of Communication Networks and Information Security, vol. 17, no. 3, pp. 527–537, 2025.
F. Arzu et al., “Real-time financial fraud detection: An intelligent data-driven framework integrating machine learning, stream processing, and big data analytics for high-velocity transaction monitoring,” The Asian Bulletin of Big Data Management, vol. 5, no. 4, pp. 124–154, 2025.
D. N. Pathak et al., “Improving e-commerce fraud detection: A GAN and reinforcement learning approach integrated with personality analysis for secure digital economy,” in Proc. International Conference on Visual Analytics and Data Visualization (ICVADV), IEEE, 2025.
U. S. Nyasala et al., “Predictive analytics with machine learning for fraud detection of online marketing transactions,” in AIP Conference Proceedings, vol. 3237, no. 1, AIP Publishing, 2025.
N. Chandra, “Using the power of artificial intelligence (AI) for fraud detection and prevention in e-commerce/online retail,” Ph.D. dissertation, University of the Cumberlands, 2025.
F. Abu-Amara, M. Alhammadi, and Z. Alhashmi, “Enhancing e-commerce security: A novel approach to credit card fraud detection,” Socialis Series in Social Science, vol. 9, pp. 117–129, 2025.
M. H. Jamil et al., “Big data analytics and its usage on financial fraud detection in the USA,” in Advances in Machine Learning IoT and Data Security, vol. 1, 2025.
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
