MACHINE LEARNING APPROACH TO CREDIT CARD FRAUD DETECTION IN SECURITY SYSTEMS
Keywords:
Credit Card Fraud, Decision Tree, Fraud Detection System, Machine LearningAbstract
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
How to Cite
Issue
Section
License
Copyright (c) 2025 Seminar Pembelajaran Sepanjang Hayat (SPSH) 2025

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.