Deep Learning for Fraud Detection in Real-Time Transaction Networks

Abstract

Abstract: The rapid expansion of digital transactions has intensified the need for real-time fraud detection systems capable of identifying anomalous patterns with high accuracy. Traditional rule-based and classical machine learning approaches often fall short in handling the complex, high-dimensional, and sequential nature of transaction data. This study investigates the application of deep learning models—specifically Convolutional Neural Networks (CNNs) and Long Short-Term Memory Recurrent Neural Networks (LSTM-RNNs)—to detect fraudulent behavior in real-time transaction networks. Using the IEEE-CIS Fraud Detection dataset, comprising over 500,000 records, the models were evaluated based on accuracy, precision, recall, and F1-score. Data preprocessing included normalization, categorical encoding, and sequence transformation. The LSTM-RNN model demonstrated superior performance, achieving 96% accuracy and an F1-score of 0.945, significantly outperforming baseline models such as logistic regression and random forest. Regression analysis further validated the stability of predictions across various transaction features. The results highlight the effectiveness of sequence-aware deep learning models in capturing subtle fraud indicators and reducing false negatives. The study underscores the importance of combining high model accuracy with low latency and interpretability for deployment in financial security systems. Keywords: deep learning, fraud detection, real-time transactions, LSTM-RNN, CNN, financial security, anomaly detection, predictive modeling, sequential data, IEEE-CIS dataset