article · Neural Computing and Applications
Credit card fraud causes substantial losses for consumers and financial institutions, yet creating robust detection tools is difficult because data privacy rules prevent banks from sharing transaction records. To bypass this restriction, federated learning was examined across both PyTorch and TensorFlow Federated frameworks. The study also tackled the severe class imbalance in transaction data, where fraudulent events represent only a tiny fraction of total activity. Various individual and hybrid resampling strategies were evaluated alongside machine learning and deep learning models. Hybrid resampling proved particularly effective for machine learning classifiers. A Random Forest classifier achieved the strongest outcomes, delivering 99.99 percent accuracy along with superior precision, recall, f-score, and minimal loss values. Additionally, while the PyTorch framework provided higher prediction accuracy in the federated configuration than TensorFlow Federated, it demanded more computational time.
Banks cannot easily share sensitive transaction data due to privacy regulations, which limits their ability to build joint anti-fraud tools. Federated learning solves this by training models across multiple institutions without exchanging raw data. Combining this approach with data balancing techniques ensures that rare instances of fraud are reliably identified, offering stronger protection against mounting financial losses for both cardholders and banks.
This research targets fraud prevention teams at banks, payment processors, and financial technology companies. Situated as applied and tested experimental research, it demonstrates how institutions could collaboratively train fraud detection models without compromising data confidentiality. Commercial adoption would involve implementing federated protocols between distinct banking infrastructures and addressing the trade-off between the higher detection accuracy and the heavier computational runtimes observed with the PyTorch framework.
AI-generated from the published abstract. Always read the original work before citing.
Abstract In recent years, credit card transaction fraud has resulted in massive losses for both consumers and banks. Subsequently, both cardholders and banks need a strong fraud detection system to reduce cardholder losses. Credit card fraud detection (CCFD) is an important method of fraud prevention. However, there are many challenges in developing an ideal fraud detection system for banks. First off, due to data security and privacy concerns, various banks and other financial institutions are typically not permitted to exchange their transaction datasets. These issues make traditional systems find it difficult to learn and detect fraud depictions. Therefore, this paper proposes federated learning for CCFD over different frameworks (TensorFlow federated, PyTorch). Second, there is a significant imbalance in credit card transactions across all banks, with a small percentage of fraudulent transactions outweighing the majority of valid ones. In order to demonstrate the urgent need for a comprehensive investigation of class imbalance management techniques to develop a powerful model to identify fraudulent transactions, the dataset must be balanced. In order to address the issue of class imbalance, this study also seeks to give a comparative analysis of several individual and hybrid resampling techniques. In several experimental studies, the effectiveness of various resampling techniques in combination with classification approaches has been compared. In this study, it is found that the hybrid resampling methods perform well for machine learning classification models compared to deep learning classification models. The experimental results show that the best accuracy for the Random Forest (RF); Logistic Regression; K-Nearest Neighbors (KNN); Decision Tree (DT), and Gaussian Naive Bayes (NB) classifiers are 99,99%; 94,61%; 99.96%; 99,98%, and 91,47%, respectively. The comparative results show that the RF outperforms with high performance parameters (accuracy, recall, precision and f score) better than NB; RF; DT and KNN. RF achieve the minimum loss values with all resampling techniques, and the results, when utilizing the proposed models on the entire skewed dataset, achieved preferable outcomes to the unbalanced dataset. Furthermore, the PyTorch framework achieves higher prediction accuracy for the federated learning model than the TensorFlow federated framework but with more computational time.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s00521-023-09410-2
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
