A Comprehensive Analysis of Machine Learning Models for Credit Card Fraud Detection

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 : 16 | 03 | Page :
    By

    Ravinder Singh,

  1. Research Analyst, Department of Management , MBA in Business Analytics, Birla Institute of Technology and Science, Pilani,, Rajasthan, India

Abstract

This paper presents an indepth comparison of various machine learning models—Logistic Regression, Support Vector Classification (SVC), and Neural Networks (NN)—in the context of credit card fraud detection. The analysis spans multiple performance metrics, including accuracy, F1 score, precision, recall, and computational efficiency. Logistic Regression demonstrates competitive performance in terms of accuracy, but its poor precision renders it unsuitable for fraud detection tasks. Conversely, the Neural Network exhibits balanced precision and recall but suffers from longer processing times, limiting its scalability. SVC emerges as the most effective model, achieving an impressive accuracy of 90.89% and recall of 79.07%, surpassing other models in detecting fraudulent transactions while minimizing false positives and false negatives. K-fold cross-validation and hyperparameter tuning further validate the model selection process, reinforcing SVC’s superiority in both performance and efficiency. Comparing the results with existing state-of-the-art approaches reveals alignment in accuracy while emphasizing the significance of data balancing techniques like SMOTE for enhanced fraud detection outcomes. This study provides valuable insights for developing efficient, scalable machine-learning solutions for credit card fraud detection in real-world applications.

Keywords: Credit card fraud detection, machine learning models, logistic regression, Support Vector Classification (SVC), data imbalance

How to cite this article:
Ravinder Singh. A Comprehensive Analysis of Machine Learning Models for Credit Card Fraud Detection. Journal of Computer Technology & Applications. 2025; 16(03):-.
How to cite this URL:
Ravinder Singh. A Comprehensive Analysis of Machine Learning Models for Credit Card Fraud Detection. Journal of Computer Technology & Applications. 2025; 16(03):-. Available from: https://journals.stmjournals.com/jocta/article=2025/view=234881


References

  1. Chapman A, Simperl E, Koesten L, Konstantinidis G, Ibáñez LD, Kacprzak E, Groth P. Dataset search: a survey. The VLDB Journal. 2020 Jan;29(1):251-72.
  2. Ruiz‐Primo A, Li M, Ayala C, Shavelson RJ. Evaluating students’ science notebooks as an assessment tool. International Journal of Science Education. 2004 Oct 8;26(12):1477-506.
  3. Preda G. Developing Kaggle Notebooks: Pave Your Way to Becoming a Kaggle Notebooks Grandmaster. Packt Publishing Ltd; 2023 Dec 27.
  4. KAVITA. Exploratory Data Analysis (EDA): Credit Card Fraud Detection Case Study. Analytics Vidhya. 2022. Available from: https://www.analyticsvidhya.com/blog/2022/03/exploratory-data- analysis-eda-credit-card-fraud-detection-case-study/
  5. Cheng D, Xiang S, Shang C, Zhang Y, Yang F, Zhang L. Spatio-temporal attention-based neural network for credit card fraud detection. InProceedings of the AAAI conference on artificial intelligence 2020 Apr 3 (Vol. 34, No. 01, pp. 362–369).
  6. Sam EF, Hamidu O, Daniels S. SERVQUAL analysis of public bus transport services in Kumasi metropolis, Ghana: Core user perspectives. Case studies on transport policy. 2018 Mar 1;6(1):25–31.
  7. Onyema JC, Betrand CU, Benson-Emenike M. Machine Learning Credit Card Fraud Detection System. Applied Sciences Research Periodicals. 2023 Sep 29;1(6):19–28.
  8. James BY, Wilson LD, Detterbeck FC. Superior vena cava syndrome—a proposed classification system and algorithm for management. Journal of Thoracic Oncology. 2008 Aug 1;3(8):811-4.
  9. Apoorva, Handa V, Batra S, Arora V. Advancing epigenetic profiling in cervical cancer: machine learning techniques for classifying DNA methylation patterns. 3 Biotech. 2024 Nov;14(11):264.
  10. Parisi L. m-arcsinh: An Efficient and Reliable Function for SVM and MLP in scikit-learn. arXiv preprint arXiv:2009.07530. 2020 Sep 16.
  11. Aldi F, Hadi F, Rahmi NA, Defit . tandardscaler’s potential in enhancing breast cancer accuracy using machine learning. Journal of Applied Engineering and Technological Science (JAETS). 2023 Dec;5(1):401-13.
  12. Heydarian M, Doyle TE, Samavi R. MLCM: Multi-label confusion matrix. Ieee Access. 2022 Feb 11;10:19083-95.
  13. Nick TG, Campbell KM. Logistic regression. Topics in biostatistics. 2007 Jan 1:273–301.
  14. Michelucci U. Unbalanced datasets and machine learning metrics. InFundamental Mathematical Concepts for Machine Learning in Science 2024 May 17 (pp. 185–212). Cham: Springer International Publishing.
  15. Zaky EH, Soliman MM, Elkholy AK, Ghali NI. IDD-HPO: A Proposed Model for Improving Diabetic Detection using Hyperparameter Optimization and Cloud Mapping Storage. International Journal of Advanced Computer Science and Applications. 2021;12(8).
  16. Ghosh D, Ganguly A, Chakraborty R, Singh PK, Li A. Performance Comparison of Different Machine Learning Classifiers for Diabetes Prediction. InInternational Conference on Computational Intelligence in Pattern Recognition 2024 Mar 15 (pp. 127–141). Singapore: Springer Nature Singapore.
  17. Bergstra J, Bardenet R, Bengio Y, Kégl B. Algorithms for hyper-parameter optimization. Advances in neural information processing systems. 2011;24.
  18. Hasanin T, Khoshgoftaar T. The effects of random undersampling with simulated class imbalance for big data. In2018 IEEE international conference on information reuse and integration (IRI) 2018 Jul 6 (pp. 70–79). IEEE.
  19. Wu YC, Feng JW. Development and application of artificial neural network. Wireless Personal Communications. 2018 Sep;102(2):1645-56.
Ahead of Print Subscription Original Research
Volume 16
03
Received 29/10/2025
Accepted 31/10/2025
Published 27/12/2025
Publication Time 59 Days
62

Login


My IP

PlumX Metrics