Paper: arXiv 2411.05815

Abstract

The landscape of financial transactions has grown increasingly complex due to the expansion of global economic integration and advancements in information technology. This complexity poses greater challenges in detecting and managing financial fraud. This review explores the role of Graph Neural Networks (GNNs) in addressing these challenges by proposing a unified framework that categorizes existing GNN methodologies applied to financial fraud detection. Specifically, by examining a series of detailed research questions, this review delves into the suitability of GNNs for financial fraud detection, their deployment in real-world scenarios, and the design considerations that enhance their effectiveness. This review reveals that GNNs are exceptionally adept at capturing complex relational patterns and dynamics within financial networks, significantly outperforming traditional fraud detection methods. Unlike previous surveys that often overlook the specific potentials of GNNs or address them only superficially, our review provides a comprehensive, structured analysis, distinctly focusing on the multifaceted applications and deployments of GNNs in financial fraud detection. This review not only highlights the potential of GNNs to improve fraud detection mechanisms but also identifies current gaps and outlines future research directions to enhance their deployment in financial systems. Through a structured review of over 100 studies, this review paper contributes to the understanding of GNN applications in financial fraud detection, offering insights into their adaptability and potential integration strategies.

Complexity vs Empirical Score

  • Math Complexity: 7.0/10
  • Empirical Rigor: 2.0/10
  • Quadrant: Lab Rats — theoretically deep, empirically untested

Why this score: The paper presents a high-level review of Graph Neural Network methodologies, featuring mathematical definitions and structural concepts, but lacks specific implementation details, code, backtests, or empirical performance metrics.

Research Flowchart

  flowchart TD
  A["Research Goal<br/>To review GNN applications<br/>in financial fraud detection"] --> B["Methodology<br/>Structured review of 100+ studies"]
  
  B --> C["Key Input<br/>Relational financial network data<br/>(Transactions & Entities)"]
  
  C --> D["Computational Process<br/>GNN Frameworks<br/>(GCN, GAT, GraphSAGE, etc.)"]
  
  D --> E{"Key Findings & Outcomes"}
  
  E --> F["Superior Performance<br/>Captures complex relational patterns<br/>outperforming traditional methods"]
  
  E --> G["Research Gaps<br/>Identified challenges in<br/>real-world deployment"]
  
  E --> H["Future Directions<br/>Guidelines for enhanced<br/>integration strategies"]
  
  F --> I["Contribution<br/>Unified framework for<br/>financial fraud detection"]

Cited References (211)

  1. Generating test data for both paths coverage and faults detection using genetic algorithms: multi-path case (2014)
  2. Wolfhard H G . Flames. 2nd ed (1960)
  3. Pre-trained Online Contrastive Learning for Insurance Fraud Detection (2024) — link
  4. Effective High-order Graph Representation Learning for Credit Card Fraud Detection (2024) — link
  5. Safeguarding Fraud Detection from Attacks: A Robust Graph Learning Approach (2024) — link
  6. Simple efficient load balancing algorithms for peer-to-peer systems (2004)
  7. Encyclopedia of Computer Science (1994)
  8. Financial Fraud Losses (2023)
and 203 more
  1. Conceptual Building of Sustainable Economic Growth and Corporate Bankruptcy (2019)
  2. THE EFFECTS OF ACCOUNTABILITY, GOVERNANCE CAPITAL, AND LEGAL ORIGIN ON REPORTED FRAUDS (2019)
  3. Credit Card Fraud Detection Using Convolutional Neural Networks (2016) — link
  4. FraudMiner: A Novel Credit Card Fraud Detection Model Based on Frequent Itemset Mining (2014) — link
  5. Detecting telecommunications fraud based on signature clustering analysis (2007)
  6. Credit card fraud detection using Bayesian and neural networks (2002)
  7. Data mining application in credit card fraud detection system (2011)
  8. Credit card fraud detection using decision tree induction algorithm (2014)
  9. On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes (2001)
  10. Detecting credit card fraud by ANN and logistic regression (2011)
  11. A Survey on Credit Card Fraud Detection Using Machine Learning (2018) — link
  12. A state of the art survey of data mining-based fraud detection and credit scoring (2018) — link
  13. A Comprehensive Survey on Graph Anomaly Detection With Deep Learning (2021) — link
  14. Blended Diffusion for Text-driven Editing of Natural Images (2021) — link
  15. LayoutGPT: Compositional Visual Planning and Generation with Large Language Models (2023) — link
  16. Explainable deep learning for efficient and robust pattern recognition: A survey of recent developments (2021)
  17. Deep Learning applied to NLP (2017) — link
  18. Ginex: SSD-enabled billion-scale graph neural network training on a single machine via provably optimal in-memory caching (2022)
  19. Graph Computing for Financial Crime and Fraud Detection: Trends, Challenges and Outlook (2020)
  20. Generalizing Aggregation Functions in GNNs: Building High Capacity and Robust GNNs via Nonlinear Aggregation (2023)
  21. Few-shot Message-Enhanced Contrastive Learning for Graph Anomaly Detection (2023)
  22. Discovering Invariant Rationales for Graph Neural Networks (2022)
  23. Competence of Graph Convolutional Networks for Anti-Money Laundering in Bitcoin Blockchain (2020) — link
  24. A survey of anomaly detection techniques in financial domain (2016) — link
  25. Enhanced Temporal Graph Embedding for Identifying Fraudulent Transactions on Transaction Networks (2021)
  26. Spatio-temporal graph representation learning for fraudster group detection (2022)
  27. Medical insurance fraud detection using graph neural networks with spatio-temporal constraints (2022)
  28. A novel spatiotemporal prediction approach based on graph convolution neural networks and long short-term memory for money laundering fraud (2022)
  29. The importance of future information in credit card fraud detection (2022)
  30. efraudcom: An e-commerce fraud detection system via competitive graph neural networks (2022)
  31. Cash-out user detection based on attributed heterogeneous information network with a hierarchical attention mechanism (2019)
  32. Ethereum fraud detection with heterogeneous graph neural networks (2022) — link
  33. MIDLG: Mutual Information based Dual Level GNN for Transaction Fraud Complaint Verification (2023)
  34. Inductive graph representation learning for fraud detection (2022)
  35. Inductive representation learning on large graphs (2017)
  36. Enhancing graph neural network-based fraud detectors against camouflaged fraudsters (2020)
  37. Learning Convolutional Neural Networks for Graphs (2016) — link
  38. Graph based anomaly detection and description: a survey (2015)
  39. Scalable and efficient full-graph gnn training for large graphs (2023)
  40. Anti-money laundering by group-aware deep graph learning (2023)
  41. Challenges and opportunities in deep reinforcement learning with graph neural networks: A comprehensive review of algorithms and applications (2023)
  42. Auc-oriented graph neural network for fraud detection (2022)
  43. Internet financial fraud detection based on graph learning (2022)
  44. Gnnguard: Defending graph neural networks against adversarial attacks (2020)
  45. Certified robustness of graph neural networks against adversarial structural perturbation (2021)
  46. Graph neural networks based detection of stealth false data injection attacks in smart grids (2021)
  47. Towards self-explainable graph neural network (2021)
  48. A visualization approach for frauds detection in financial market (2009)
  49. Edge direction and the structure of networks (2010)
  50. A novel potential edge weight method for identifying influential nodes in complex networks based on neighborhood and position (2022)
  51. Strategies for Pre-training Graph Neural Networks (2019)
  52. Pre-training on large-scale heterogeneous graph (2021)
  53. Gcc: Graph contrastive coding for graph neural network pre-training (2020)
  54. Pre-trained Online Contrastive Learning for Insurance Fraud Detection (2024)
  55. User behavior pre-training for online fraud detection (2022)
  56. Deep learning applications and challenges in big data analytics (2015)
  57. Intelligent financial fraud detection: a comprehensive review (2016)
  58. Pagraph: Scaling gnn training on large graphs via computation-aware caching (2020)
  59. GraphFM: Improving large-scale GNN training via feature momentum (2022)
  60. Efficient data loader for fast sampling-based gnn training on large graphs (2021)
  61. Pre-training graph neural network for cross domain recommendation (2021)
  62. Learning to pre-train graph neural networks (2021)
  63. Netprobe: a fast and scalable system for fraud detection in online auction networks (2007)
  64. Explainable graph-based fraud detection via neural meta-graph search (2022)
  65. Know-gnn: An explainable knowledge-guided graph neural network for fraud detection (2021)
  66. Contrastive graph neural network-based camouflaged fraud detector (2022)
  67. TTAGN: Temporal transaction aggregation graph network for ethereum phishing scams detection (2022)
  68. Adversarial attack and defense on graph data: A survey (2022)
  69. SCN_GNN: A GNN-based fraud detection algorithm combining strong node and graph topology information (2024)
  70. ASA-GNN: Adaptive Sampling and Aggregation-Based Graph Neural Network for Transaction Fraud Detection (2023)
  71. Dynamic graph neural network-based fraud detectors against collaborative fraudsters (2023)
  72. Financial Anti-Fraud Based on Dual-Channel Graph Attention Network (2024)
  73. Adaptive Attention-Based Graph Representation Learning to Detect Phishing Accounts on the Ethereum Blockchain (2024)
  74. Fraud detection based on graph neural networks with self-attention (2021)
  75. MAG-GNN: Reinforcement Learning Boosted Graph Neural Network (2024)
  76. LaundroGraph: Self-Supervised Graph Representation Learning for Anti-Money Laundering (2022)
  77. Using GNN to detect financial fraud based on the related party transactions network (2022)
  78. MAFI: GNN-based multiple aggregators and feature interactions network for fraud detection over heterogeneous graph (2021)
  79. Financial fraud: A literature review (2019)
  80. Anti-money laundering: Using data visualization to identify suspicious activity (2019)
  81. Competence of graph convolutional networks for anti-money laundering in bitcoin blockchain (2020)
  82. Inspection-L: self-supervised GNN node embeddings for money laundering detection in bitcoin (2023)
  83. Flowscope: Spotting money laundering based on graphs (2020)
  84. Temporal debiasing using adversarial loss based GNN architecture for crypto fraud detection (2021)
  85. On the potential of a graph attention network in money laundering detection (2022)
  86. Semi-supervised credit card fraud detection via attribute-driven graph representation (2023)
  87. Graph neural network for credit card fraud detection (2021)
  88. Parallel granular neural networks for fast credit card fraud detection (2002)
  89. Fighting against organized fraudsters using risk diffusion-based parallel graph neural network (2023)
  90. Uncovering insurance fraud conspiracy with network learning (2019)
  91. PaGraph: Scaling GNN training on large graphs via computation-aware caching (2020) — link
  92. Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness (2023) — link
  93. Dynamic Graph Neural Networks Under Spatio-Temporal Distribution Shift (2022) — link
  94. Representation learning for dynamic graphs: A survey (2020)
  95. Graphlime: Local interpretable model explanations for graph neural networks (2022)
  96. Causal attention for interpretable and generalizable graph classification (2022)
  97. Gnnexplainer: Generating explanations for graph neural networks (2019)
  98. Simple and deep graph convolutional networks (2020)
  99. Personalized Embedding Propagation: Combining Neural Networks on Graphs with Personalized PageRank (2018) — link
  100. Graph Attention Networks (2018) — link
  101. Predicting multicellular function through multi-layer tissue networks (2017)
  102. Link prediction based on graph neural networks (2018)
  103. Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning (2020)
  104. The link-prediction problem for social networks (2007)
  105. Graph convolutional neural networks for web-scale recommender systems (2018)
  106. Neural graph collaborative filtering (2019)
  107. Neural message passing for quantum chemistry (2017)
  108. Convolutional networks on graphs for learning molecular fingerprints (2015)
  109. Community detection in graphs (2010)
  110. A Spatial–Temporal Gated Network for Credit Card Fraud Detection by Learning Transactional Representations (2023)
  111. Modularity and community structure in networks (2006)
  112. How powerful are graph neural networks? (2018) — link
  113. Spectral networks and locally connected networks on graphs (2013) — link
  114. Semi-supervised classification with graph convolutional networks (2017)
  115. Auto-encoder based Graph Convolutional Networks for Online Financial Anti-fraud (2019) — link
  116. Anti-money laundering in Bitcoin: Experimenting with graph convolutional networks for financial forensics (2019)
  117. Hierarchical multi-modal fusion on dynamic heterogeneous graph for health insurance fraud detection (2022)
  118. Graph neural network-based bitcoin transaction tracking model (2023)
  119. Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics (2019) — link
  120. Structural temporal graph neural networks for anomaly detection in dynamic graphs (2021)
  121. Temporal graph representation learning for detecting anomalies in e-payment systems (2021)
  122. EWS-GCN: Edge Weight-Shared Graph Convolutional Network for Transactional Banking Data (2020) — link
  123. Solve fraud detection problem by using graph based learning methods (2019) — link
  124. Scalable graph learning for anti-money laundering: A first look (2018) — link
  125. A Spatio-Temporal Attention-Based GCN for Anti-money Laundering Transaction Detection (2023)
  126. Temporal-aware graph neural network for credit risk prediction (2021)
  127. A Semi-Supervised Graph Attentive Network for Financial Fraud Detection (2019) — link
  128. Heterogeneous graph neural networks for malicious account detection (2018)
  129. Modeling heterogeneous graph network on fraud detection: A community-based framework with attention mechanism (2021)
  130. GoSage: Heterogeneous Graph Neural Network Using Hierarchical Attention for Collusion Fraud Detection (2023)
  131. A comprehensive survey on graph anomaly detection with deep learning (2021)
  132. DGA-GNN: Dynamic Grouping Aggregation GNN for Fraud Detection (2024)
  133. H2-fdetector: A gnn-based fraud detector with homophilic and heterophilic connections (2022)
  134. Realistic synthetic financial transactions for anti-money laundering models — → 2306.16424
  135. Graphical network models for international financial flows (2016)
  136. Enhancing financial fraud detection with hierarchical graph attention networks: A study on integrating local and extensive structural information (2023)
  137. Credit card fraud detection using time series analysis (2014)
  138. An entropy-based approach for measuring complexity in supply chains (2010)
  139. Towards a new urban geography of expenditure: Using bank card transactions data to analyze multi-sector spatiotemporal distributions (2022)
  140. Explainable fraud detection of financial statement data driven by two-layer knowledge graph (2024)
  141. MedGraph: malicious edge detection in temporal reciprocal graph via multi-head attention-based GNN (2023)
  142. Attention-based graph neural network for identifying illicit bitcoin addresses (2021)
  143. A GNN-based Fraud Detector with Dual Resistance to Graph Disassortativity and Imbalance (2024)
  144. A Synergistic Approach for Graph Anomaly Detection With Pattern Mining and Feature Learning (2022) — link
  145. Graph neural network for fraud detection via spatial-temporal attention (2020)
  146. Bright-graph neural networks in real-time fraud detection (2022)
  147. Medicare fraud detection using graph neural networks (2022)
  148. Alleviating the inconsistency problem of applying graph neural network to fraud detection (2020)
  149. Heterogeneous mini-graph neural network and its application to fraud invitation detection (2020)
  150. Live-streaming fraud detection: a heterogeneous graph neural network approach (2021)
  151. Suspicious Massive Registration Detection via Dynamic Heterogeneous Graph Neural Networks (2021)
  152. T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction (2019)
  153. Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks (2019)
  154. Dynamic Network Embedding: An Extended Approach for Skip-gram based Network Embedding (2018)
  155. A review of data mining-based financial fraud detection research (2007)
  156. A Review of Financial Accounting Fraud Detection based on Data Mining Techniques (2012)
  157. A systematic analysis and guidelines of graph neural networks for practical applications (2021)
  158. Intention-aware heterogeneous graph attention networks for fraud transactions detection (2021)
  159. Dual-augment graph neural network for fraud detection (2022)
  160. Heterogeneous graph neural networks for fraud detection and explanation in supply chain finance (2024)
  161. Graph neural networks: A review of methods and applications (2020)
  162. Financial fraud detection using graph neural networks: A systematic review (2023)
  163. Financial fraud detection applying data mining techniques: A comprehensive review from 2009 to 2019 (2021)
  164. Financial fraud detection based on machine learning: a systematic literature review (2022)
  165. Intelligent fraud detection in financial statements using machine learning and data mining: a systematic literature review (2021)
  166. Multimodal data fusion: an overview of methods, challenges, and prospects (2015)
  167. A Comprehensive Survey on Graph Neural Networks (2020)
  168. COMPA: Detecting Compromised Accounts on Social Networks (2013)
  169. Dynamic relation-attentive graph neural networks for fraud detection (2023)
  170. Complex networks in finance (2016)
  171. BRIGHT – Graph Neural Networks in Real-Time Fraud Detection (2022) — link
  172. Financial fraud detection using quantum graph neural networks (2024) — link
  173. Financial Fraud Detection with Graph Data Science: Analytics and Feature Engineering (2020)
  174. New feature engineering framework for deep learning in financial fraud detection (2021)
  175. Exploiting edge features for graph neural networks (2019)
  176. Generalizing aggregation functions in gnns: High-capacity gnns via nonlinear neighborhood aggregators (2022) — link
  177. Edge-labeling based modified gated graph network for few-shot learning (2024)
  178. Sampling from large graphs (2006)
  179. Auto insurance fraud detection with multimodal learning (2023)
  180. AutoFraudNet: A Multimodal Network to Detect Fraud in the Auto Insurance Industry (2023) — link
  181. Multi-modality self-attention aware deep network for 3D biomedical segmentation (2020)
  182. SAFFNet: Self-attention-based feature fusion network for remote sensing few-shot scene classification (2021)
  183. Multi-modal graph interaction for multi-graph convolution network in urban spatiotemporal forecasting (2022)
  184. MMGCN: Multi-modal graph convolution network for personalized recommendation of micro-video (2019)
  185. Gcnet: Graph completion network for incomplete multimodal learning in conversation (2023)
  186. Graphsmote: Imbalanced node classification on graphs with graph neural networks (2021)
  187. Graph-based approaches for over-sampling in the context of ordinal regression (2014)
  188. $ M $-channel oversampled graph filter banks (2014)
  189. Ensemble-GNN: federated ensemble learning with graph neural networks for disease module discovery and classification (2023)
  190. Boosting-GNN: boosting algorithm for graph networks on imbalanced node classification (2021)
  191. Cost-Sensitive GNN-Based Imbalanced Learning for Mobile Social Network Fraud Detection (2023)
  192. Dual cost-sensitive graph convolutional network (2022)
  193. Attention and Cost-Sensitive Graph Neural Network for Imbalanced Node Classification (2022)
  194. An adaptive two-layer light field compression scheme using GNN-based reconstruction (2020)
  195. Meta-path-based heterogeneous graph neural networks in academic network (2022)
  196. Heterogeneous graph attention network (2019)
  197. Discovering meta-paths in large heterogeneous information networks (2015)
  198. The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature (2011)
  199. Predicting systemic risk in financial systems using Deep Graph Learning (2023) — link
  200. Graph Attention Networks (2018) — link
  201. Financial time series forecasting with multi-modality graph neural network (2022)
  202. Subgraph Patterns Enhanced Graph Neural Network for Fraud Detection (2024)
  203. Relation-Aware Heterogeneous Graph Neural Network for Fraud Detection (2024)

1 of 211 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.