Full Text PDF
Impact Factor (2025): 6.9
DOI Prefix: 10.47001/IRJIET
Impact Factor (2025): 6.9
DOI Prefix: 10.47001/IRJIET
Vol 10 No 5 (2026): Volume 10, Issue 5, May 2026 | Pages: 441-447
International Research Journal of Innovations in Engineering and Technology
OPEN ACCESS | Research Article | Published Date: 22-05-2026
Payment fraud is a problem when people use someone else credentials to buy things online. This can cause a lot of trouble for merchants and consumers. To stop this from happening a system that uses machine learning is being suggested. This system looks at transaction data as it happens to find fraud. The system works by looking at the details of each transaction that is sent to the admin panel. It then matches these details to see if they are legitimate or not. The system uses a few models to make predictions, including Logistic Regression, Random Forest, Support Vector Machine and XGBoost. When getting the data ready the system looks at things like how much money's being spent what time it is, where the transaction is happening and how many transactions are happening at the same time. The system is trained using a mix of real transactions, which helps it get really good at telling the difference between the two. The results show that XGBoost is the model with 96.20% accuracy 94.90% precision and 93.80% recall for finding fraud. This means the system can help the admin approve or reject payments and stop payments right away. This makes online shopping safer by reducing the number of payments that get through and, by making things happen faster. One thing that could be a problem is that the system needs data to work well. In the future the system could be improved by making it work in time all the time. Limitations include dependency on feature quality, with future enhancements in real-time streaming.
E-commerce Payment Fraud, Machine Learning, Fraud Detection, Online Transactions, Payment Security, Transaction Classification, Random Forest, XGBoost, Fraud Prediction.
Ajahar Pathan, Mayur More, Bhavesh Patel, Milind Dikshit, & Tejas Marathe. (2026). E-Commerce Fraud Detection System Using Machine Learning. International Research Journal of Innovations in Engineering and Technology - IRJIET, 10(5), 441-447. Article DOI https://doi.org/10.47001/IRJIET/2026.105061
This work is licensed under Creative common Attribution Non Commercial 4.0 Internation Licence
Vijayasri, G. (2025). Online Payment Fraud Detection Using Machine Learning Techniques. International Conference on Advanced Computing and Engineering Systems.
Dalal, S., et al. (2022). Optimized XGBoost Model for Financial Payment Fraud Detection. Mathematics, 10(24), 4679.
Sarmini, R., et al. (2024). E-commerce Fraud Detection Using Random Forest and XGBoost with CGAN-Based Data Augmentation. Bulletin of Information Technology.
Ibrahim, M., & Alfauzan, A. (2025). Performance Analysis of Machine Learning Models for Online Payment Fraud Detection. Journal of Artificial Intelligence Research and Applications.
Hafid, A. (2024). Fraud Detection on Imbalanced Payment Transaction Datasets Using Random Forest and XGBoost. Khatulistiwa Journal of Applied Research and Technology.
FraudX AI Research Team. (2025). FraudX AI: Explainable Machine Learning Framework for Fraud Detection on Imbalanced Datasets. Computers Journal, 14(4), 120.
Ajahar I. Pathan, Ketan Patil, Dipak Patil, Harshal Patil, Jayashree Patil, and Tejaswini Patil, “Application to Detect Fake Reviews Using CNN and Advanced Machine Learning Techniques,” International Research Journal of Modernization in Engineering Technology and Science (IRJMETS), vol. 7, no. 6, June 2025.
Enehikhare, E., & Odumuyiwa, V. (2025). Comparative Analysis of Machine Learning Algorithms for Fraud Detection in Imbalanced Transaction Datasets. University of Ibadan Journal of ICT Research.
AjaharIsmailkha Pathan, Liladhar M. Kuwar, Rijavan A. Shaikh, Dheeraj Basant Shukla, “Removing Duplicate Data in Cloud Environment using Secure Inverted Index Method”, International Research Journal of Engineering and Technology (IRJET), Volume: 05 Issue: 09, Page 157-161,Sep 2018.
Odugbile, T. (2025). Deployable Machine Learning Approaches for Real-Time Credit Card Fraud Detection. SSRN Electronic Journal.
Tax, N., et al. (2021). Machine Learning-Based Fraud Detection in E-commerce: Research Challenges and Future Directions. arXiv Preprint arXiv:2107.01979.