MACHINE LEARNING APPROACH TO CREDIT CARD FRAUD DETECTION IN SECURITY SYSTEMS

Authors

  • Nasywa Naura Aulia Universitas Multimedia Nusantara, Indonesia
  • SY Yuliani Yakub Universitas Multimedia Nusantara, Indonesia
  • Nin Hayati Mohd Yusoff Politeknik Merlimau Melaka, Malaysia

Keywords:

Credit Card Fraud, Decision Tree, Fraud Detection System, Machine Learning

Abstract

The rapid growth of digital transactions has heightened the risk of credit card fraud, creating significant challenges for financial security. Traditional detection methods often struggle to process the scale and complexity of transaction data. This study proposes a conceptual framework for a machine learning–based fraud detection system, outlining systematic stages including data collection, preprocessing to handle imbalance and noise, feature selection, model training, and evaluation using performance metrics such as precision, recall, and F1-score. The Decision Tree algorithm is highlighted as the core method due to its interpretability and ability to identify transaction patterns through Entropy and Information Gain. The contribution of this study lies in providing a clear and structured roadmap for developing machine learning–driven fraud detection systems. Unlike most prior studies that only compare algorithmic accuracy, this framework emphasizes adaptive handling of class imbalance and lays the foundation for integration into real-time fraud detection systems.

Downloads

Published

30-11-2025

How to Cite

Aulia, N. N., Yakub, S. Y. ., & Mohd Yusoff, N. H. . (2025). MACHINE LEARNING APPROACH TO CREDIT CARD FRAUD DETECTION IN SECURITY SYSTEMS. SPSH 2025, 184–200. Retrieved from https://spsh.mypolycc.edu.my/proceedings/index.php/spsh2025/article/view/396

Issue

Section

Engineering, Industry 4.0, Smart Technologies & Security