2026· Proceedings of the 15th International Conference on Data Science, Technology and Applications· 0 citations· 20 references
TL;DR
This work provides a mathematically grounded benchmarking framework for integrating Explainable Artificial Intelligence (XAI) into fraud detection pipelines, aligning high-accuracy analytics with the transparency requirements expected in regulated financial environments.
Abstract
: This study proposes an optimized ensemble framework for highly imbalanced credit card fraud detection that jointly maximizes predictive sensitivity and model interpretability. While machine learning offers significant potential for high-dimensional financial data analysis, its adoption is often hindered by extreme data sparsity and the inherent “black-box” nature of complex ensemble architectures. To bridge this gap, we develop a comprehensive pipeline incorporating six high-performance classifiers, fine-tuned via the Optuna Bayesian optimization framework. Leveraging a benchmark European dataset with a 0 . 172% fraud rate, our methodology employs a hybrid strategy of synthetic oversampling and cost-sensitive learning, integrated with SHapley Additive exPlanations (SHAP) to deconstruct complex decision boundaries. Empirical findings indicate that XGBoost delivers a superior Precision-Recall Area Under the Curve (PR-AUC) of 0 . 8755, while the Random Forest (RF) model achieves an optimal F 2 -Score (0 . 8673), effectively minimizing undetected fraudulent events. Our analysis further identifies time-of-day signals in the engineered temporal representation as relevant indicators of malicious activity. This work provides a mathematically grounded benchmarking framework for integrating Explainable Artificial Intelligence (XAI) into fraud detection pipelines, aligning high-accuracy analytics with the transparency requirements expected in regulated financial environments.
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
Sophisticated machine learning and deep learning architectures often achieve high predictive performance but remain insufficient for high-stakes domains such as financial fraud detection, where stakeholders require both accuracy and trust in the decision-making process. This study proposes a weighted ensemble framework that strategically combines eXtreme Gradient Boosting (XGBoost) and Graph SAmple and aggreGatE (GraphSAGE) models to optimize the precisionrecall trade-off while maintaining interpretability. Our proposed framework, BoostSAGE, leverages complementary strengths of its constituent models. XGBoost provides high precision (94%) through transaction-level feature analysis, while GraphSAGE ensures superior recall (95%) by capturing structural risk signals across transaction-user-merchant relationships. Empirical results indicate that BoostSAGE outperforms constituent models by synthesizing local and relational feature sets. Most notably, the ensemble delivers a 14.97% improvement in AUCPR over the XGBoost baseline. By leveraging historical fraud aggregation within user-centric connections, the model reduces total False Negatives by 44.8% compared to XGBoost, yielding a final F1score of 92.88%. Our results demonstrate that weighted ensemble framework provides a robust and interpretable approach to fraud detection, balancing operational efficiency with stakeholder trust.
Chaw Thet Zan, Yusuke Maruyama, Felix Beierle· Annual International Compute...· 0 citations
Accurate credit card fraud detection is crucial for financial system security. Under class imbalance, existing models struggle with the precision–recall trade-off: traditional Focal Loss relies on static parameters that cannot adapt to sample difficulty, conventional fusion strategies are parameter-sensitive and prone to extreme weight assignments, and a single model often fails to capture both complex nonlinear patterns and robust structural features. This study proposes the FL-XGB Fusion framework, which adopts a decoupled warm-up scheduling strategy for Focal Loss—an adaptive class balancing coefficient α targeting the empirical fraud rate, and a progressively increasing focusing parameter γ preventing premature suppression of hard examples—together with a Bayesian temperature-optimized adaptive fusion network that quantifies prediction uncertainty via information entropy, dynamically allocates DNN and XGBoost weights, and employs TPE sampling to search for the optimal temperature per fold. Experiments on three heterogeneous datasets (IEEE-CIS, CreditCard, and PaySim) under five-fold stratified cross-validation show that the framework achieves the highest F1-Score among eight baseline methods on all three datasets, improving over standalone XGBoost by 1.51–1.81 pp, while remaining competitive in AUC-ROC. Ablation studies with nine variants and non-parametric tests quantify the contribution of each core component, indicating that the gains, though modest in magnitude, are consistent across the three datasets with different imbalance ratios.
Jiaxin Yang, Danmei Zhu, Zaichao Wang et al.· Scientific Reports· 0 citations
As financial fraud becomes increasingly sophisticated, the demand for complex machine learning models has surged, inadvertently leading to a significant increase in computational energy consumption. This study addresses the critical trade-off between predictive accuracy and environmental sustainability within a Green AI framework. We propose a multi-objective optimization approach to evaluate Logistic Regression, Random Forest, and XGBoost on a highly imbalanced credit card fraud dataset. Experimental results reveal a non-linear “Carbon Cost of Complexity,” where the transition from linear to tree-based architectures yields diminishing returns; a 3.4% improvement in detection accuracy requires a 163% increase in training carbon emissions. The Random Forest model $(\mathbf{n}=\mathbf{2 0 0}, \mathbf{d}=\mathbf{1 5})$ emerged as the Pareto Optimal solution, achieving a superior F1-Score of 0.7512 and an AUPRC of 0.8031. Although XGBoost proved to be 62% more energy-efficient during the training phase, Random Forest demonstrated a distinct advantage in inference latency, achieving a throughput of 664,576 Transactions Per Second (TPS). We conclude that while Random Forest incurs a higher carbon footprint $\left(\mathbf{7. 1 5} \times \mathbf{1 0}^{-\mathbf{6}} \mathbf{~ k g C O} \mathbf{2 e q}\right.$ per cycle), this expenditure is justified by its robustness in preventing financial loss and its capability for real-time processing in high-stakes environments.
Ebenhaezer George Renaldi Muljadi, Albert Justin, F. Ardan et al.· 2026 11th International Conf...· 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
The evaluation of accounting transactions is increasingly challenging due to the growing volume of financial records, severe class imbalance, and the limited transparency of existing audit support systems. Many current machine learning approaches emphasize prediction accuracy while providing insufficient interpretability and weak support for risk-oriented audit decisions. To address these issues, this paper proposes an Intelligent Accounting framework based on explainable machine learning for risk-oriented transaction outcome prediction. The proposed framework integrates accounting-driven feature engineering, supervised learning, SHAP based explainable artificial intelligence, and probability-based risk scoring into a unified decision-support pipeline. Logistic Regression is adopted as the core predictive model due to its robustness, interpretability, and model parsimony under highly imbalanced transaction data. Experimental results on accounting dataset consisting of 1,000 transaction records show that Logistic Regression achieved the highest PR-AUC of 0.9737 and ROC-AUC of 0.6458 compared with Random Forest and XGBoost. The risk scoring mechanism also ranked problematic transactions within the highest-risk group, supporting audit prioritization. In addition, graphical SHAP analysis provides qualitative insights by identifying Operating Expenses, log_Operating Expenses, transaction timing, Transaction Volume, Profit Margin, Revenue, Expenditure, Cash Flow, Gross Profit, and Accuracy Score as influential factors affecting transaction outcomes. These findings show that the proposed framework not only predicts transaction outcomes but also explains the accounting factors behind each decision. Overall, this study transforms conventional transaction classification into an interpretable, risk-oriented, and audit-driven intelligent accounting system for transparent financial decision support.
J. K. Siregar, Astari Dianty, Antonius Bimo Rentor et al.· International Seminar on Int...· 0 citations