This work presents FinFraudBench, a heterogeneous graph benchmark for financial fraud detection, and establishes a standardized evaluation protocol covering both ranking and imbalance-sensitive classification metrics, and evaluates representative baselines.
Abstract
The increasing complexity of digital financial systems has reshaped financial fraud detection from isolated transaction classification into relational risk reasoning over interconnected financial entities. This shift has motivated graph-based fraud detection, where models identify fraudulent nodes by exploiting dependencies among customers, cards, merchants, categories, and locations. However, despite rapid progress in graph-based methods, existing public benchmarks remain misaligned with real-world financial systems in two important aspects. First, they often simplify financial ecosystems into homogeneous or single-node-type multi-relational graphs, failing to preserve the multi-entity and multi-relational nature of financial data. Second, they rarely provide large-scale heterogeneous financial graph datasets with realistic operating conditions such as extreme class imbalance and limited label availability, making it difficult to assess the practical effectiveness of current methods. To address these gaps, we present FinFraudBench, a heterogeneous graph benchmark for financial fraud detection. FinFraudBench contains two heterogeneous graph datasets (CreditCard-Fraud and BankTrans-Fraud) with up to 8.99M nodes and 89.23M directed typed edges. Each dataset preserves six financial entity types, fourteen directed edge types, and natural fraud rates that mirror deployment constraints. With these datasets, we establish a standardized evaluation protocol covering both ranking and imbalance-sensitive classification metrics, and evaluate representative baselines. Extensive experiments yield empirical insights into current methods'limitations and suggest promising avenues for future research. FinFraudBench is available at https://anonymous.4open.science/r/FinFraudBench-B002.
This work constructs and makes publicly available a comprehensive U.S. company dataset combining financial statements, summarized MD&A text, and fraud labels and achieves the best performance on the challenging CI-FSFD task, demonstrating the critical value of textual data and robust evaluation for reliable financial fraud detection.
Guy Stephane Waffo Dzuyo, Gaël Guibon, Christophe Cerisara et al.· arXiv.org· 0 citations
The complexity and volume of transactional data has expanded due to the rapid growth of digital financial services, which has opened the door to new types of sophisticated fraud. The ever-changing nature of fraud trends and the complexity of entity interactions make rule-based or transactional fraud detection systems inadequate. Using relational structure learning and transactional behaviour profiling, FraudGraph-X is a multimodal graph neural framework for behavioural fraud detection. In the financial ecosystem model offered by the framework, users, accounts, devices, and merchants are nodes in a graph. Graph neural networks analyse transactional histories, patterns of activity across time, and ambient metadata to identify group fraud tendencies and high-order dependencies. Unlike conventional methods, FraudGraph-X is able to learn from structural links and behavioural indicators, allowing it to detect complex and organised fraud. Based on thorough experimental testing on real-world and benchmark financial datasets, the system outperforms non-graph deep learning approaches, conventional machine learning, and the detection accuracy of changing fraud tactics. It also has lower false positive rates. Using multimodal graph learning, FraudGraph-X can discover intricate fraud patterns; it is a smart and scalable solution for fraud detection systems of the future.
N. Yatoo, M. Jishnu, Josiah John et al.· ITM Web of Conferences· 0 citations
Digital financial ecosystems face mounting exposure to fraudulent transactions that collectively account for trillions of dollars in losses each year. Existing approaches suffer from three recurring deficiencies: they represent all transaction participants within a single undifferentiated node space, rely on fixed decision boundaries incapable of accommodating evolving fraud distributions, and fail to exploit the semantic diversity among entity categories including accounts, merchants, and transaction types. This study introduces FHT-GraphSAGE, a federated heterogeneous temporal graph learning framework for privacy-preserving financial fraud detection. The architecture combines heterogeneous temporal graph construction, a relation-aware GraphSAGE encoder with sinusoidal temporal edge embeddings, and a Federated Averaging optimization scheme that enables cross-institutional collaborative learning without exposing raw transaction records. Evaluation across two complementary benchmarks, the PaySim Mobile Money Dataset and the Credit Card Fraud 2023 Dataset, demonstrates consistent superiority over ten competitive baselines. On PaySim, FHT-GraphSAGE achieves an accuracy of 0.963, an F1-score of 0.939, an AUC-ROC of 0.986, and, most importantly under severe class imbalance, an AUC-PR of 0.724. On the Credit Card Fraud 2023 Dataset, it attains an accuracy of 0.941, an F1-score of 0.913, an AUC-ROC of 0.969, and an AUC-PR of 0.721. As AUC-PR is the most informative metric for minority-class detection under extreme imbalance, these two figures (0.724 and 0.721) constitute the primary evidence of the framework’s fraud-detection capability. Results are reported as the mean over five independent runs with distinct random seeds, and the improvements over the strongest baseline are statistically significant (p < 0.01). Ablation experiments confirm the non-redundant contribution of each architectural component, and robustness evaluations demonstrate stable minority-class detection performance down to a fraud ratio of 0.25%.
S. Islam, Md. Abul Kalam Azad, A. Masum et al.· International Journal of Adv...· 0 citations
Financial fraud is becoming increasingly complex alongside the growth of digital financial ecosystems, causing conventional fraud detection approaches based on handcrafted rules and tabular machine learning models to face limitations in identifying coordinated fraudulent activities. This study aims to analyze the application of Graph Neural Networks (GNNs) for financial fraud detection by utilizing transaction attributes and graph structural information. A quantitative experimental approach was conducted using the publicly available Elliptic Bitcoin Transaction Dataset, where transactions were modeled as graph nodes and relationships between transactions as graph edges. The proposed method implemented a Graph Attention Network (GAT) and compared its performance with Graph Convolutional Networks (GCN), GraphSAGE, and Graph Isomorphism Networks (GIN). Data preprocessing involved feature normalization, graph construction, and supervised learning on labeled transaction data. Model evaluation was performed using Accuracy, Precision, Recall, F1-score, ROC-AUC, and PR-AUC metrics. The results show that attention-based graph learning provides superior performance in detecting fraudulent transactions by assigning adaptive importance to relevant neighboring nodes during information propagation. Furthermore, graph representation learning effectively captures interconnected fraud patterns that are difficult to identify using conventional machine learning methods. These findings highlight the potential of GNNs as an intelligent approach for improving financial fraud detection and supporting risk management systems in increasingly complex digital financial environments.
E. Setiawati· JURNAL ILMIAH SAINS TEKNOLOG...· 5 citations· ⚡1
The typical approach to fraud detection in retail environments relies on rules-based, static detection engines. Such systems perform well against simple, known attack types but struggle against sophisticated, emerging threats and organized financial syndicates. Moreover, rules-based systems produce high false positive rates that seriously degrade the experience of legitimate customers. This paper presents a Graph Artificial Intelligence framework to support high-throughput and streaming retail transactions with built-in explainability. Our approach treats transactions as a dynamic and heterogeneous graph to capture complex relational dependencies and structural anomalies in real time. We validate the framework using a curated subset of the publicly available IEEE-CIS Fraud Detection dataset under a streaming scenario, evaluating both latency and predictive accuracy. Combined with PyTorch Geometric for graph neural network construction and SHAP (Shapley Additive exPlanations) for post-hoc model interpretation, our system delivers high prediction accuracy and human-interpretable decision making. The proposed model shows strong accuracy and recall compared to traditional baselines, while flagged transactions are explained through visual subgraph evidence. This transparency enables fraud analysts to validate alerts efficiently, reducing review time and operational cost in e-commerce environments.
Jose Prabhu Michael Singarayan, Jayakumar Ramalingam, Neetu Uthaman· 2026 International Conferenc...· 0 citations
: In this big data-driven era, the digital characteristics of financial credit are constantly undergoing strengthening, the financial relationship network is becoming increasingly sophisticated, and the forms of credit fraud faced are becoming more severe, which poses a serious threat to the security of financial market transactions and the stable development of the economy. Based on the present situation, this article discusses a categorized approach to detection, starting with the satisfaction of functional requirements. Specifically, it explores detection methods based on graph neural networks from both the perspectives of non-functional and functional requirements, and then clarifies their strengths and weaknesses. Furthermore, the article explores detection methods that combine LLM and graph neural networks. Finally, this article introduces commonly used datasets and proposes several feasible solutions to their limitations, such as data imbalance and privacy protection. In the context of financial credit fraud based on graph neural networks, the comprehensive application of a variety of detection strategies, assisted by LLM and federated learning, will further enhance the robustness and accuracy of financial fraud detection, safeguard the stable operation of financial markets, and promote sustainable economic development.
Cong-Ling Zheng· Proceedings of the 3rd Inter...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
