Aug 2026· International Journal of Engineering Research and Science & Technology· 0 citations
TL;DR
Experimental results demonstrate that TabNet outperforms traditional neural networks and popular machine learning algorithms by achieving high fraud detection accuracy with significantly reduced false alarms while maintaining excellent interpretability suitable for financial regulatory requirements.
Abstract
Credit card fraud has emerged as one of the most significant challenges faced by financial institutions due to the rapid growth of digital banking and online transactions. Traditional machine learning algorithms often struggle to maintain high detection accuracy while minimizing false positives, particularly in highly imbalanced transaction datasets. This paper proposes an interpretable deep learning framework based on the TabNet architecture for enhancing credit card fraud detection in banking systems. Unlike conventional neural networks, TabNet employs sequential attention mechanisms to perform feature selection dynamically, enabling superior learning from structured tabular transaction data while providing model interpretability. The proposed methodology includes comprehensive data preprocessing, missing value handling, feature scaling, class imbalance correction using SMOTE, and hyperparameter optimization. Experimental evaluation is conducted on the publicly available European Credit Card Fraud Detection dataset. Performance is evaluated using Accuracy, Precision, Recall, F1-score, ROC-AUC, PR-AUC, and Matthews Correlation Coefficient (MCC). Experimental results demonstrate that TabNet outperforms traditional neural networks and popular machine learning algorithms by achieving high fraud detection accuracy with significantly reduced false alarms while maintaining excellent interpretability suitable for financial regulatory requirements. Recent studies have similarly reported strong performance of TabNet for banking fraud detection, highlighting its suitability for structured financial datasets and explainable AI applications.
Credit card fraud remains a major challenge for financial institutions, both financially and operationally, as digital transactions continue to grow and fraud datasets remain highly imbalanced. This study compares the performance of several supervised machine learning models for fraud detection, using a unified data preprocessing pipeline. The approach includes removing duplicates, applying RobustScaler normalization, engineering features and using the Synthetic Minority Oversampling Technique (SMOTE) to balance classes before training. Four models were developed and tested Logistic Regression, Decision Tree, Random Forest and Artificial Neural Network (ANN) using the publicly available Kaggle Credit Card Fraud Detection dataset. Their performance was measured with Accuracy, Precision, Recall, F1-score and ROC-AUC metrics. Results showed that thorough preprocessing combined with SMOTE significantly improved the models ability to detect fraudulent transactions. Among them, the Random Forest model delivered the strongest overall performance, proving especially effective at handling highly imbalanced financial data. The comparative analysis also highlighted that ensemble learning methods generally outperform single classifiers in both accuracy and minority-class recognition. These findings emphasize the importance of pairing robust preprocessing strategies with machine learning techniques to boost fraud detection in real-world financial systems. The proposed system offers institutions a scalable and practical solution for building intelligent fraud detection systems, while laying the groundwork for future integration of Explainable AI (XAI) and real-time detection tools.
Nafiu Yahuza, Ahmad Baita Garko, Abubakar Atiku Muslim et al.· Lead Sci Journal of Manageme...· 0 citations
Abstract The rise in online transactions has made credit card fraud a significant global concern, necessitating detection strategies that are both highly accurate and practically viable. While existing literature extensively explores machine learning techniques to address class imbalance, most studies optimize for traditional statistical metrics, overlooking the asymmetric financial costs and strict operational constraints of real-world fraud detection. This study bridges this gap by proposing a comprehensive, cost-sensitive ensemble framework evaluated on a real-world European cardholder dataset. We move beyond the traditional F 1 score by adopting the cost-sensitive F β metric to reflect real financial impact. Through exhaustive benchmarking, we show that while eXtreme Gradient Boosting (XGBoost) combined with Borderline SMOTE achieves the highest single-model performance, our proposed soft-voting ensemble integrating Logistic Regression and Random Forest with SMOTE delivers the best overall performance (F β = 0.8287). To ensure practical viability, we introduce a Top-K operational constraint evaluation reflecting limited human investigation bandwidths. Additionally, an ablation study demonstrates that there is no universal remedy for class imbalance; optimal interventions are highly model-dependent. Finally, by validating our framework on a feature-transparent simulated dataset, model interpretability analysis reveals the ensemble’s capacity to capture the critical importance of environmental risk factors, shifting the focus beyond solely customer-centric anomalies.
Xinyue Fan, T. Boonen· Asia-Pacific Journal of Risk...· 0 citations
The study shows that machine learning can be useful for fraud detection when it is combined with suitable preprocessing, class-imbalance techniques, and careful evaluation.
Jabulani Khumalo, Min Joon Kim· Global Knowledge Academy· 0 citations
Financial institutions are highly concerned about credit card fraud due to its significant impact on their financial losses. Detecting fraud is challenging as fraudsters are constantly adapting to new technology. To protect customers and businesses, it is crucial to have a robust fraud detection system. This study proposes a novel machine learning approach for detecting credit card fraud using Bayesian Gaussian Mixture Model (BGMM). The study contributes by processing the complex, multi-featured credit card dataset using an Autoencoder model to reduce its dimensionality. The reduced data is clustered in a low-dimensional space using the BGMM to separate fraudulent from normal transactions. The Gibbs sampler algorithm was used to estimate the parameters in the BGMM. The proposed model was evaluated and compared with baseline models, including the Gaussian Mixture Model (GMM) with EM algorithm, K-means, Autoencoder, and Isolation Forest, on two public datasets, Kaggle ULB and IEEE-CIS, using AUC-ROC scores. The results demonstrate that the proposed method achieves the best performance on the Kaggle ULB dataset and competitive, stable performance on the IEEE-CIS dataset, achieving an AUC-ROC score of 0.9672 on the Kaggle ULB dataset and 0.5422 on the IEEE-CIS dataset under a leakage-free unsupervised learning protocol. The adoption of the proposed approach will aid financial institutions and credit card companies in enhancing their fraud detection systems, resulting in greater accuracy and efficiency in detecting fraudulent transactions.
Suboh M. Alkhushayni, Du’a Al-zaleq, M. Alsmadi et al.· Discover Artificial Intellig...· 0 citations
A novel hybrid CNN-AdaBoost framework, where convolutional neural networks extract intricate, complex patterns from raw transactional features, and AdaBoost performs robust iterative classification to refine predictions, outperforming standalone methods on imbalanced fraud detection.
An AI-Based Credit Card Fraud Detection System using Machine Learning to identify suspicious transactions accurately and in the real time and improves prediction accuracy through sequential learning and optimized decision trees.
P. Ravikumar, Gowrav A. S., A. N et al.· International Journal of Inn...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
