Deep Learning for Real-Time Fraud Detection: Enhancing Credit Card Security in Banking Systems

Abstract

In this study, we present a deep learning-based approach for real-time credit card fraud detection in banking systems, with a primary focus on Long Short-Term Memory (LSTM) networks. Using a highly imbalanced credit card transaction dataset, we implemented comprehensive preprocessing, feature engineering, and model evaluation strategies to enhance the detection accuracy. Our experimental results reveal that the LSTM model significantly outperformed traditional machine learning algorithms such as Logistic Regression, Decision Tree, and Random Forest. The LSTM achieved an accuracy of 99.38%, precision of 99.40%, recall of 99.22%, and F1-score of 99.31%, demonstrating its superior capability to detect fraud while minimizing false positives. Through comparative analysis, we establish that deep learning not only improves predictive performance but also adapts better to temporal patterns inherent in financial transactions. This research underscores the transformative potential of AI-driven fraud detection in modern banking infrastructures, ensuring enhanced security, operational efficiency, and customer trust.