Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62526
Volume:
10 |
5 |
May 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer science and engineering
Bharath institute of higher education and research
Computer science and engineering
Bharath institute of higher education and research
Computer science and engineering
Bharath institute of higher education and research
Computer science and engineering
Bharath institute of higher education and research
Computer science and engineering
Bharath institute of higher education and research
Digital transactions have become an essential part of Financial fraud in digital transactions can result in modern financial systems, enabling fast and substantial losses for both individuals and convenient payments through platforms such as UPI, credit cards, and online banking. However, the increasing reliance on these systems has also led to a rise in fraudulent activities, creating serious security challenges for both users and financial institutions. Detecting such fraud using traditional rule-based approaches is difficult due to the dynamic and complex nature of modern attack patterns. This paper presents a machine learning-based fraud organizations. Traditional fraud detection systems mainly rely on predefined rules and thresholds to identify suspicious behavior. While these systems are effective for detecting simple fraud patterns, they are often unable to adapt to new and sophisticated attack strategies. As fraudsters continuously evolve their techniques, static rule-based systems become less reliable. To address these challenges, machine learning has detection framework designed to analyze emerged as a powerful approach for fraud detection. transactions across multiple payment methods. The proposed system evaluates various behavioral and transactional features, including transaction amount, location patterns, device information, account history, and transaction frequency. Advanced classification techniques such as Random Forest and XGBoost are employed to identify irregular patterns and assess the likelihood of fraudulent activity. Machine learning models can analyze large volumes of transaction data, learn patterns of normal user behavior, and identify deviations that mayindicate fraudulent activity. These models are capable of newadapting todata and improving their performance over time.
KEYWORDS
The proposed Intelligent Multi-Payment Fraud Detection System provides an effective solution for identifying fraudulent transactions in modern digital payment environments. By leveraging machine learning techniques such as Random Forest and XGBoost, the system is capable of analyzing transaction patterns and detecting suspicious activities with high accuracy. The integration of multiple features, including transaction amount, location, device information, and user behavior, enhances the system's ability to identify complex fraud patterns
[1] X. Feng, Y. Li, and Z. Wang, "A Novel Machine Learning Based Credit Card Fraud Detection Method," Mathematics, vol. 12, no. 12, pp. 1–15, 2024. [2] A. Cherif, M. Kortebi, and A. K. Samet, "Credit Card Fraud Detection in the Era of Disruptive Technologies," Journal of King Saud University Computer and Information Sciences, vol. 35, no. 3, pp. 1-10, 2023. [3] E. A. L. M. Btoush et al., “Enhancing Credit Card Fraud Detection Using Stacking Models," 2025. [Online]. Available: https://pmc.ncbi.nlm.nih.gov/ [4] M. Tayebi et al., "Enhanced XGBoost Algorithm for Fraudulent Transaction Detection," 2025. [Online]. Available: https://www.sciencedirect.com/ [5] I. Popova, "Credit Card Fraud Detection Using Machine Learning Models," arXiv preprint, 2025. [Online]. Available: https://arxiv.org/ [6] J. Shi, "Credit Card Fraud Detection Based on ANN and XGBoost," Proc. Int. Conf., 2024. [Online]. Available: https://www.scitepress.org/ [7] L. Theodorakopoulos, "Credit Card Fraud Detection with Machine Learning," Preprints, 2024. [Online]. Available: https://www.preprints.org/ [8] N. Baisholan, “Systematic Review of Machine Learning in Credit Card Fraud Detection," Computers, vol. 14, no. 10, pp. 1-20, 2025. [9] B. M. Naman, "Credit Card Fraud Detection Based on Machine Learning Classification Algorithms," 2024. [Online]. Available: https://www.researchgate.net/ [10] X. Asnawi, “Application of XGBoost Classification for Fraud Detection," Journal of Computer Engineering and Systems, 2025.
Publication Date
5/5/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
2
Total views since publication
PDF Downloads
6
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...