Enhancing Credit Card Fraud Detection Using Device Fingerprinting and Behavioral Biometrics

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2025 | Volume : 13 | Issue : 02 | Page : 40 50
    By

    Sakshi Vinod Jadhav,

  • Gayatri Balasaheb Joshi,

  • Deesha Shashikant Pasoli,

  • Sanika Balkrishna Kashid,

  • Ambuj Kumar,

  1. Student, Department of Computer Engineering. Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology, Khapalur, Maharashtra, India
  2. Student, Department of Computer Engineering. Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology, Khapalur, Maharashtra, India
  3. Student, Department of Computer Engineering. Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology, Khapalur, Maharashtra, India
  4. Student, Department of Computer Engineering. Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology, Khapalur, Maharashtra, India
  5. Professor, Department of Computer Engineering. Vishwaniketan’s Institute of Management Entrepreneurship and Engineering Technology, Khapalur, Maharashtra, India

Abstract

Credit card fraud is a growing global concern, with financial losses projected to reach $ 43.47 billion by 2028. Credit card fraud poses a major challenge in the financial industry, resulting in substantial financial losses and security risks. This research introduces a Machine Learning-based Credit Card Fraud Detection System designed to improve the accuracy of fraud identification. Due to the imbalanced nature of fraud datasets, SMOTE (Synthetic Minority Over-sampling Technique) was applied to improve model training. Various classification algorithms, such as Logistic Regression, Support Vector Machine (SVM), Random Forest, and XG Boost, were applied and optimized. Among them, XG Boost achieved the best performance, effectively minimizing false positives and negatives. The project also explores potential future enhancements, including device fingerprinting and behavioral biometrics, to further improve fraud detection. Device fingerprinting would analyze unique user characteristics such as IP addresses, browser settings, and hardware configurations to detect anomalies in transaction behavior. Behavioral biometrics, focusing on typing speed, mouse movement,
and transaction behavior patterns, could help identify fraudulent activities based on deviations from a user’s normal interactions. The attached analysis of transaction data and fraud trends highlights key fraud patterns and model performance insights. The findings suggest that integrating machine learning with future security enhancements like device fingerprinting and behavioral biometrics could significantly improve real-time fraud detection, making financial transactions more secure.

Keywords: Credit card fraud, fraud detection, machine learning, XG Boost, card-not-present fraud, device fingerprinting, behavioral biometrics, transaction security, fraud prevention

[This article belongs to Journal Of Network security ]

How to cite this article:
Sakshi Vinod Jadhav, Gayatri Balasaheb Joshi, Deesha Shashikant Pasoli, Sanika Balkrishna Kashid, Ambuj Kumar. Enhancing Credit Card Fraud Detection Using Device Fingerprinting and Behavioral Biometrics. Journal Of Network security. 2025; 13(02):40-50.
How to cite this URL:
Sakshi Vinod Jadhav, Gayatri Balasaheb Joshi, Deesha Shashikant Pasoli, Sanika Balkrishna Kashid, Ambuj Kumar. Enhancing Credit Card Fraud Detection Using Device Fingerprinting and Behavioral Biometrics. Journal Of Network security. 2025; 13(02):40-50. Available from: https://journals.stmjournals.com/jons/article=2025/view=207939


References

  1. Chaudhary K, Yadav J, Mallick B. A review of fraud detection techniques: Credit card. Int J Comput Appl. 2012 May; 45(1): 39–44.
  2. Lakshmi SV, Kavilla SD. Machine learning for credit card fraud detection system. Int J Appl Eng Res. 2018; 13(24): 16819–24.
  3. Jain Y, Tiwari N, Dubey S, Jain S. A comparative analysis of various credit card fraud detection techniques. Int J Recent Technol Eng. 2019 Jan; 7(5): 402–7.
  4. Moalosi M, Hlomani H, Phefo OS. Combating credit card fraud with online behavioural targeting and device fingerprinting. International Journal of Electronic Security and Digital Forensics (IJESDF). 2019; 11(1): 46–69.
  5. 6Raju O. Credit Card Fraud Detection Using XGBoost Classifier. International Journal of Techno- Engineering (IJTE). 2021; 3(2021): 14–27.
  6. Yousefi N, Alaghband M, Garibay I. A comprehensive survey on machine learning techniques and user authentication approaches for credit card fraud detection. arXiv preprint arXiv:1912.02629. 2019 Dec 2.
  7. Adapa SR, Nirob MA, Bhatt S, Yerram M, Nivas AP. Enhancing Credit Card Fraud Detection: A Novel Approach with Random Forest and Behavioral Biometrics. Int J Res Appl Sci Eng Technol. 2024; 12(3): 2858–2866.
  8. Moskovitch R, Feher C, Messerman A, Kirschnick N, Mustafic T, Camtepe A, Lohlein B, Heister U, Moller S, Rokach L, Elovici Y. Identity theft, computers and behavioral biometrics. In 2009 IEEE International Conference on Intelligence and Security Informatics. 2009 Jun 8; 155–160.
  9. Stylios I, Kokolakis S, Thanou O, Chatzis S. Behavioral biometrics & continuous user authentication on mobile devices: A survey. Inf Fusion. 2021 Feb 1; 66: 76–99.
  10. Rayani PK, Changder S. Continuous user authentication on smartphone via behavioral biometrics: a survey. Multimed Tools Appl. 2023 Jan; 82(2): 1633–67.
Regular Issue Subscription Original Research
Volume 13
Issue 02
Received 17/03/2025
Accepted 01/04/2025
Published 15/04/2025
Publication Time 29 Days
434

Login


My IP

PlumX Metrics