Fraud Detection in Online Payments

Madhavi Dixit; Syed Mohammed Tahir; Mohammed Abuzar; Mohammed Maaz Sheikh K; Mohammed Salman

doi:10.22161/eec.ncastem.2025-3

Indexing and Abstracting

Fraud Detection in Online Payments

Madhavi Dixit , Syed Mohammed Tahir , Mohammed Abuzar , Mohammed Maaz Sheikh K , Mohammed Salman

International Journal of Electrical, Electronics and Computers (IJECC), Vol-11,Issue-1 (Special Issue-NCASTEM), January - February 2026, Pages 16-22, 10.22161/eec.ncastem.2025-3

Download | Downloads : 5 | Total View : 376

Article Info: Received: 18 Nov 2025; Accepted: 01 Feb 2025; Date of Publication: 07 Feb 2026

Abstract:

The Web-based financial payments are increasingly targeted by fraud schemes, making automated detection systems an urgent need. This study explores a range of machine-learning approaches that can be used to detect fraudulent transactions and analyzes how integrating different types of input data can enhance classification accuracy. A fraud-detection framework developed with widely used benchmark datasets and enriched with several related features shows strong potential for practical use beyond controlled research settings. A major factor behind the improved performance is the use of sophisticated feature-selection strategies, where evolutionary optimization techniques such as Genetic Algorithms eliminate unnecessary variables while preserving the most informative ones. Thoughtful feature engineering, combined with resampling strategies and adjustments for class imbalance, plays a crucial role in strengthening digital-payment security and reinforcing cybersecurity defenses. During evaluation, ensemble models based on boosting especially gradient boosting produced the most accurate predictions, with comparatively fewer misclassified cases. However, the reliability of the overall system still depends heavily on the quality of the data, and expert review remains essential to manage false alarms that may appear due to bias or overlapping behavioral patterns. An effective fraud-detection workflow progresses through several stages: gathering raw data, removing noise and inconsistencies, selecting appropriate models, conducting controlled testing, validating performance on unseen transactions, and monitoring results after deployment. Implementing such learning-driven security solutions helps minimize financial losses while building greater confidence in digital payments for both consumers and businesses. Future progress in this area is expected to focus on learning from movement- and time-based patterns, including regional trends and temporal anomalies, and on incorporating adaptive drift- monitoring systems to better respond to evolving fraud tactics

Keywords:

Artificial Intelligence, Anomaly Detection, Final Fraud, Fraud Detection, Machine Learning, Online Payments Fraud, Random Forest, XGBoost Classifier.

References:

[1] A. R. Sharma and M. Jain, ―Ensemble anomaly detection using LightGBM for online fraud detection,‖ Expert Systems with Applications, vol. 210, 2023.
[2] V. Patel, S. Menon, and H. Ramesh, ―Trandormer- based sequential models for online fraud detection,‖ Procedia Computer Science, vol.221, pp. 123-132, 2023.
[3] D. Kumar and R. Saini, ―Improved online fraud detection using SMPTE with XGBoost and LightGBM,‖ Information Sciences, vol. 622, pp. 378- 390, 2023.
[4] M. Srivastava and K. Sharma, ―Enhanced Random forest usig SMOTE for class-imbalanced fraud datasets,‖ Journal of Financial Data Science, vol. 4, no, 2, pp. 33-45, 2023.
[5] A. Mishra, R. Jain, and M. Gupta, ―Voting-based ensemble model for online payment fraud detection,‖ International Journal of Information Management Data Insights, vol. 3, no. 1, 2023.
[6] H Khan and N. Ali, ―A hybrid autoencoder and gradient boosting approach for fraud detection in online payments,‖ Neural Computing and Applications, vol, 35, pp. 12560-12574, 2023.
[7] S. Reddy and K. Rao, ―Machine learning-based fraud detection with random oversampling,‖ Journal of King Saud University – Computer and Information Sciences, vol. 35, no. 2, pp. 195-202, 2023.
[8] P. Jain, R. Sharma, and L. Das, ―Comparative evaluation of CNN, SVM, and KNN for online payment fraud detection,‖ Computers in Industry, vol.144, 2023.
[9] R. Ahmed and A. Gupta, ―Layered machine learning architecture for adaptive fraud detection,‖ Journal of Big Data, vol. 10, Article no. 72, 2023.
[10] A. Chatterjee and T. Banerjee, ―Fraud detection in transaction sequences using Transformer-based deep models, ―IEEE Transcations on Neural Networks and Learning Systems, vol. 34, no.1, pp. 39-52, 2023.
[11] P. Singh and R. Kaur, ―Dense neural network applications in anti-money laundering systems,‖ Applied Soft Computing, vol. 128, 2023.
[12] S. Kumar and N. Verma, ―Real-time fraud detection using Apache Spark and Isolation Forest,‖ Future Generation Computer Systems, vol. 142, pp. 712-725, 2023.
[13] R. Srinivasan and S. Mehta, ―AI-enhanced fraud detection in real-time payment systems,‖Computational Intelligence, vol. 39, no. 4, pp. 453–467, 2024.
[14] M. Hussain and K. Prasad, ―Online transaction fraud detection system based on machine learning,‖ Journal of Intelligent Systems, vol. 32, no. 3, pp. 455–468, 2023.
[15] T. Ramesh and R. Purohit, ―Review paper on UPI fraud detection using machine learning,‖International Journal of Emerging Technology and Advanced Engineering, vol. 13, no. 1, 2023.
[16] S. Nair and A. Shah, ―Comparative study of ML algorithms
for fraud detection,‖ Procedia Computer Science, vol. 215,
pp. 456–463, 2023.
[17] R. Chandra and A. Patil, ―Credit card fraud analysis using machine learning techniques,‖ Materials Today: Proceedings, vol. 74, no. 2, 2024.
[18] J. Fernandes and L. Thomas, ―Fraud detection on payments using credit card, online transactions and banking data,‖ Journal of Applied Security Research, vol. 18, no. 1, pp. 12– 28, 2024.
[19] P. Sharma and G. Kulkarni, ―Optimized deep learning approach for detecting fraudulent transactions,‖ Neural Processing Letters, vol. 57, no. 1, pp. 125–140, 2023.
[20] A. Bhattacharya and S. De, ―Machine learning techniques for fraud detection in online payment systems,‖ Information and Software Technology, vol. 150, 2023

International Journal Of Electrical, Electronics And Computers(IJEEC)

For Authors

Issues

Downloads

Indexing and Abstracting

Fraud Detection in Online Payments

Abstract:

Keywords:

References: