Enhancing Payment Security Using Machine Learning

  • Unique Paper ID: 172993
  • Volume: 11
  • Issue: 9
  • PageNo: 1518-1523
  • Abstract:
  • Detecting fraudulent financial transactions represents an essential banking system priority dedicated to safeguarding customer trust and decreasing financial losses. This research analyzes fraud detection through the BankSim synthetic dataset that contains transaction information including amount details alongside demographic traits and merchant identifiers. Because the dataset featured a significant unbalance between legitimate and fraudulent transaction records SMOTE became indispensable for addressing this class imbalance challenge. The research deployed KNN Random Forest and XGBoost classification algorithms and subsequently developed an ensemble system for superior predictive accuracy. Experimentation resulted in KNN alongside XGBoost and the ensemble classifier producing 99% accurate results maintaining Random Forest at 98% accuracy. The study confirms how modern machine learning approaches together with ensemble learning deliver remarkable success in detecting fraudulent incidents. This research delivers essential understanding of building dependable automated analysis tools for detecting financial transaction fraud.

Copyright & License

Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{172993,
        author = {Shaik Sharon Raju and Ms. E. Vinothini and S. Bharath Kumar Reddy and M.S. Roobini},
        title = {Enhancing Payment Security Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {9},
        pages = {1518-1523},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=172993},
        abstract = {Detecting fraudulent financial transactions represents an essential banking system priority dedicated to safeguarding customer trust and decreasing financial losses. This research analyzes fraud detection through the BankSim synthetic dataset that contains transaction information including amount details alongside demographic traits and merchant identifiers. Because the dataset featured a significant unbalance between legitimate and fraudulent transaction records SMOTE became indispensable for addressing this class imbalance challenge. The research deployed KNN Random Forest and XGBoost classification algorithms and subsequently developed an ensemble system for superior predictive accuracy. Experimentation resulted in KNN alongside XGBoost and the ensemble classifier producing 99% accurate results maintaining Random Forest at 98% accuracy. The study confirms how modern machine learning approaches together with ensemble learning deliver remarkable success in detecting fraudulent incidents. This research delivers essential understanding of building dependable automated analysis tools for detecting financial transaction fraud.},
        keywords = {Fraud detection, BankSim dataset, Synthetic Minority Oversampling Technique (SMOTE), KNN, XGBoost, ensemble learning.},
        month = {February},
        }

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 9
  • PageNo: 1518-1523

Enhancing Payment Security Using Machine Learning

Related Articles