Detecting Fraud in Online Payments from Historical Transaction Data using Machine Learning
DOI:
https://doi.org/10.21467/proceedings.7.6.27Keywords:
Logistic Regression, Random Forest, SMOTEAbstract
Online fraud detection is vital for maintaining financial security and mitigating transaction risks. This study utilized historical transaction data to develop a fraud detection system using logistic regression and random forest models. Both models were trained and evaluated on a dataset containing highly imbalanced fraudulent and non-fraudulent transactions. Random forest, due to its ensemble learning nature, demonstrated superior performance in detecting fraudulent activities, handling data imbalance effectively, and achieving high precision and ROC-AUC scores. Logistic regression provided an interpretable alternative with lower computational complexity. Evaluation metrics such as accuracy, precision, recall, F1-score, and ROC-AUC were employed to compare the models. The random forest model achieved a precision of 98.5% and ROC-AUC of 0.998, outperforming logistic regression in all key areas. The results highlight the effectiveness of ensemble methods for real-time fraud detection and the role of machine learning in securing online payments.
References
[1] R. Patel, A. Sharma, and P. Gupta, “Fraud detection in online payment transaction using machine learning algorithms,” IEEE Conf. Publ., 2024.
[2] V. Jain, “Perspective analysis of telecommunication fraud detection using data stream analytics and neural network classification,” J. Emerg. Technol. Innov. Res., 2024.
[3] Y. Zhu, L. Zhu, and J. Bai, “Fraud detection in online payments using machine learning techniques,” in Proc. IEEE Int. Conf. Big Data, 2024.
[4] X. Wang, H. Zhao, and M. Chen, “Real-time fraud detection in online payments with gradient boosting models,” Elsevier, 2023.
[5] F. K. Alarfaj, I. Malik, H. U. Khan, N. Almusallam, M. Ramzan, and M. Ahmed, “Credit card fraud detection using state-of-the-art machine learning and deep learning algorithms,” IEEE Access, 2025.
[6] S. Vimal, K. Kayathwal, H. Wadhwa, and G. Dhama, “Application of deep reinforcement learning to payment fraud,” in Proc. KDD Workshop on Multi-Armed Bandits and Reinforcement Learning, 2021.
[7] S. Soni, S. Kanojiya, S. Yadav, R. Arakh, and R. Shukla, “Online payment fraud detection system using convolution neural network,” Int. J. Comput. Sci. Technol., 2024.
[8] M. Seera, C. P. Lim, A. Kumar, L. Dhamotharan, and K. H. Tan, “An intelligent payment card fraud detection system,” Ann. Oper. Res., 2024.
[9] D. S. Das, R. Ghosh, and P. Mitra, “A graph-based machine learning approach for detecting suspicious transactions in online payments,” J. Financial Data Sci., vol. 5, no. 3, pp. 112–126, 2024.
[10] V. Rao, S. Iyer, and A. Nair, “Deep learning framework using autoencoders for credit card fraud detection,” IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 1, pp. 98–110, 2024.
[11] Z. Zhang, X. Zhou, and X. Zhang, “A convolutional neural network-based model for detecting online transaction fraud,” Secur. Commun. Netw., 2023.
[12] X. Zhang, H. Liu, and J. Wang, “Fraud online payment detection based on machine learning with balancing data technique,” in IET Conf. Publ., IEEE Xplore, 2024.
[13] S. Gupta and R. K. Sharma, “Credit card fraud detection using random forest and neural networks,” IEEE Trans. Neural Netw., vol. 35, no. 4, pp. 987–995, 2023.
[14] J. Lee and M. K. Singh, “A hybrid machine learning model for financial fraud detection,” IEEE Trans. Big Data, vol. 10, no. 2, pp. 543–555, 2023.
[15] L. Wu, P. Zhang, and C. Sun, “Anomaly-based fraud detection in online transactions using deep learning,” IEEE Access, vol. 12, pp. 45521–45532, 2024.
[16] D. Ramesh and K. Patel, “Real-time online payment fraud detection with XGBoost algorithm,” in Proc. IEEE Int. Conf. Mach. Learn. Appl. (ICMLA), pp. 789–796, 2023.
[17] F. Al-Bahrani, T. Yousaf, and R. Chen, “Graph-based approach for detecting anomalous transactions in online payments,” IEEE Trans. Comput. Intell. AI Finance, vol. 4, no. 1, pp. 33–45, 2024.
[18] A. Kumar, S. Das, and V. Menon, “Comparative analysis of supervised and unsupervised machine learning for fraud detection,” in Proc. IEEE Conf. Artif. Intell. Finance (ICAIF), pp. 112–118, 2023.
[19] C. Miller and D. Fox, “Explainable AI for online payment fraud detection,” in Proc. IEEE Symp. AI Ethics (AISAE), pp. 221–229, 2024.
[20] M. R. Ahmed and H. S. Kim, “Deep learning for credit card fraud detection in financial transactions,” in Proc. IEEE Int. Conf. Data Sci. Adv. Anal. (DSAA), pp. 401–408, 2024.
[21] T. Archana and R. K. Stephen, “The future of artificial intelligence in manufacturing industries,” in Industry Applications of Thrust Manufacturing: Convergence with Real-Time Data and AI, IGI Global, pp. 98–117, 2024.
[22] A. Thirugnanam and F. B. J. Hussain, “Exploring machine learning algorithms for the prediction of dengue: A comprehensive review,” Revue d'Intelligence Artificielle, vol. 37, no. 5, 2023.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
