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.
Abstract
Detecting credit card fraud remains a critical issue in financial security, demanding models that excel on imbalanced tabular transaction data while balancing accuracy, interpretability,
and efficiency.
This paper proposes 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.
We evaluate the approach on standard credit card fraud benchmarks, achieving an overall accuracy of 95.43% alongside a strong F1-score of 92.75%, surpassing baselines methods. Ablation studies also conducted to confirm synergy: standalone CNN yields 93.12% accuracy, while pure AdaBoost reaches 93.58%, highlighting how feature fusion addresses individual shortcomings in handling noise and class imbalance.
The novelty stems from repurposing CNN’s convolution layers to capture local, complex patterns directly from raw tabular transaction data, feeding these rich representations into AdaBoost for adaptive error correction. This hybrid uniquely blends deep feature learning’s nuance with ensemble boosting’s efficiency and interpretability, outperforming standalone methods on imbalanced fraud detection. Prior works rarely fuse these for tabular domains, yielding our 95.43% accuracy benchmark.
This provides valuable insights into the design of hybrid models for structured and tabular data classification tasks and establishes a strong benchmark for future research in this domain.
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.
G Srividhya, Dr. S Siva Sankara Rao· International Journal of Eng...· 0 citations
Credit card fraud is a menace to financial institutions, but detection is compromised by highly imbalanced transaction datasets. This study proposes an advanced machine learning framework optimized for fraud detection. To address the issue of data imbalance, SMOTE-Tomek Links is applied to synthetically generate minority fraud cases while removing noisy, overlapping majority-class instances. Recursive Feature Elimination (RFE) is deployed to identify the optimal features, and RandomizedSearchCV automates hyperparameter optimization. The study introduces a Stacked Logistic Regression ensemble to combine the predictive capacity of optimized Random Forest and XGBoost base classifiers. The model’s effectiveness is assessed using seven evaluation methods: accuracy, recall, precision, confusion matrix, F1-score, Receiver Operating Characteristic Area Under the Curve (ROC-AUC) score and the Area Under the Precision-Recall Curve (AUC-PR) score. Findings reveal that the proposed stacked model performance surpasses both individual base models. While achieving deceptively high baseline accuracy across all models, the stacked ensemble delivers a superior AUC-PR score of 0.8207 and an F1-score of 0.93. This minimizes the confusion matrix misclassifications to just 20 False Negatives and 5 False Positives. The framework provides a cost-optimized operational engine that aggressively mitigates bank fraud losses while successfully shielding legitimate cardholders from accidental checkout declines.
Uduh Israel Akakoh, G. N. Edegbe· FUDMA Journal of Sciences· 0 citations
Financial fraud detection presents a significant challenge due to the extreme class imbalance inherent in transaction datasets. This paper presents a comprehensive evaluation of deep learning architectures for fraud detection in structured transaction data, with a focus on model performance, interpretability, and operational relevance. Specifically, we compare three deep tabular models, namely, an advanced multilayer perceptron (AdvancedMLP), an attention‐based residual network (AttentionFraudNet), and an advanced residual network (AdvancedResNet), against three traditional machine learning baselines, including Random Forest, Gradient Boosting, and Logistic Regression. The experiments are conducted on the BankSim Simulator dataset, comprising 594,643 transactions with a fraud rate of approximately 1.21%. We evaluate models using multiple metrics, including PR‐AUC, ROC‐AUC, recall at low false positive rates, and precision at various operating thresholds. Our results show that AdvancedMLP achieves the highest PR‐AUC (0.8921 ± 0.0020), while Gradient Boosting attains the best ROC‐AUC (0.9987 ± 0.0001) and the highest recall at 1% FPR (0.9498 ± 0.0087). AttentionFraudNet provides interpretable attention weights that highlight transaction‐level features contributing to fraud predictions, enabling fraud analysts to understand and validate model decisions. Business impact analysis reveals that the proposed models can reduce fraud losses while maintaining false positive rates below 1%, translating to estimated annual savings of approximately 49.2 M$ for a mid‐sized financial institution. All models achieve inference times below 1 ms per transaction on an NVIDIA RTX 3090 GPU, demonstrating computational feasibility for near‐real‐time screening. Our findings highlight the effectiveness of deep tabular models for fraud detection and provide practical guidance for selecting models based on operational requirements and performance trade‐offs.
Vahid Azarvand, Parvin Azhdari, A. Beitollahi· Engineering Reports· 0 citations
Click fraud remains one of the most pressing threats in digital advertising, inflating campaign costs and distorting marketing analytics. Conventional detection approaches are frequently unable to adapt to sophisticated and evolving fraud patterns. This study proposes an explainable hybrid framework that integrates deep learning and gradient boosting for ad click fraud detection using the Kaggle Ad Click Fraud Detection Dataset (5,000 records, 21 features). During preprocessing, multicollinearity was systematically removed through Pearson correlation analysis (threshold ρ > 0.85), reducing the feature set from 21 to 14 highly discriminative attributes. Random Under-Sampling (RUS) and SMOTE were applied to correct class imbalance. Thirteen classical machine learning and deep learning models were benchmarked, including CNN, DNN, RNN, LSTM, GRU, and hybrid LSTM–GRU networks. A Voting Classifier combining XGBoost and Bagging with Decision Tree served as the proposed architecture, achieving 100% accuracy, precision, recall, and F1-score. Explainability was incorporated through LIME (local, per-prediction waterfall explanations) and SHAP (global feature importance rankings). A Flask-based web interface enables real-time fraud prediction. The architecture demonstrates inference latency below 50 ms per request, making it suitable for large-scale, real-time advertising platforms.
Salma Banu S, J. R· 2026 7th International Confe...· 0 citations
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
Credit cards are now the primary tool for digital transactions due to the quick expansion of e-commerce and cashless payment ecosystems. As a result, fraudulent activity has grown proportionately, resulting in significant financial losses for banks, retailers, and cardholders. On the benchmark European cardholder dataset, the authors' previous work investigated single-model Random Forest (RF) classification, a hybrid RF-SVM voting scheme, and a hybrid SVM-Logistic Regression (LR) scheme, with accuracies of 96.6%, 98.0%, and 98.2%, respectively. Despite their effectiveness, these methods are nonetheless susceptible to the dataset's high class imbalance (0.17% fraud), depend on a tiny number of base learners, and offer fraud analysts and regulators no way to evaluate their conclusions. By proposing SMOTE-Stack-XAI, a stacked ensemble framework that (i) uses the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance, (ii) combines four heterogeneous base learners—Random Forest, XGBoost, Support Vector Machine (SVM), and a Deep Neural Network (DNN)—through a Logistic-Regression meta-learner, and (iii) integrates SHapley Additive exPlanations (SHAP) to reveal the transaction-level features that influence each fraud decision. The suggested framework is assessed using Accuracy, Precision, Recall, F1-score, and AUC on the same dataset of 284,807 European cardholder transactions. According to experimental results, SMOTE-Stack-XAI outperforms the RF, hybrid RF-SVM, and hybrid SVM-LR baselines with an accuracy of 99.3%, precision of 99.2%, recall of 99.4%, and F1-score of 99.3%. It also produces human-interpretable, feature-level explanations for each prediction, making the model appropriate for real-time, auditable fraud-detection pipelines.
Bhukya Dharma, D. Latha· International journal of com...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
