Graph-Based Financial Fraud Detection with Calibrated Risk Scoring and Structural Regularization
Summary
This paper proposes a graph neural network framework for financial fraud detection that integrates transaction records and identity information into node attributes, employs a multi-layer message passing mechanism, and uses weighted supervision and structural consistency regularization to improve risk scoring and probability calibration. Experiments on a public dataset show the method outperforms existing approaches.
View Cached Full Text
Cached at: 05/14/26, 06:18 AM
# Graph-Based Financial Fraud Detection with Calibrated Risk Scoring and Structural Regularization Source: [https://arxiv.org/abs/2605.12782](https://arxiv.org/abs/2605.12782) [View PDF](https://arxiv.org/pdf/2605.12782) > Abstract:Financial transaction fraud prevention faces challenges such as complex relationship structures, concealed behavioral patterns, and dynamically changing data distribution\. Discrimination models relying solely on independent sample features are insufficient to fully characterize the risks of group collaboration and chain transfers within transaction networks\. This paper proposes a graph neural network representation learning and risk discrimination framework for financial transaction fraud prevention\. It integrates transaction records and identity information into node attributes and constructs a transaction graph based on shared attributes and interaction consistency to explicitly model inter\-transaction relationships\. In model design, a multi\-layer message passing mechanism is employed to aggregate neighborhood information, learn node embedding representations containing structural context semantics, and output transaction\-level fraud probability and risk scores through a lightweight risk discrimination head\. A weighted supervision objective is introduced to mitigate training bias caused by class imbalance, and structural consistency regularization constraints are combined to suppress the impact of noisy edges on representation drift, thereby improving the stability and usability of risk characterization\. Experiments are conducted on a publicly available financial transaction dataset, comparing various methods in the same direction and comprehensively evaluating them under a unified evaluation protocol\. The results show that the proposed method outperforms other methods in risk ranking and probability calibration quality, validating the effectiveness of graph structure modeling and representation learning collaboration in financial transaction fraud prevention\. ## Submission history From: Yuhan Wang \[[view email](https://arxiv.org/show-email/b0453833/2605.12782)\] **\[v1\]**Tue, 12 May 2026 21:52:24 UTC \(1,086 KB\)
Similar Articles
TMR-GGNN: Credit Card Fraud Detection based on Time-Aware Multi-Relational Guided Graph Neural Network
Proposes TMR-GGNN, a time-aware multi-relational graph neural network for credit card fraud detection that handles imbalanced data and evolving fraud patterns via contrastive learning and focal loss.
Quantum-Inspired Contextual Learning for Sparse-Ring Fraud Detection in Dynamic Transaction Graphs
This paper presents an exploratory benchmark for detecting sparse-ring fraud in dynamic transaction graphs using quantum-inspired Contextual Machine Learning (CML) compared to a GRU baseline, finding that hybrid graph features combining identity-preserving and topological summaries yield the best results.
Graph-Driven Cross-Industry Real-Time Monitoring Framework for Anti-Money Laundering Detection in Converged Mobility-Energy Supply Chain Networks
This paper proposes a graph-driven real-time anti-money laundering monitoring framework (GCRMF) for cross-industry supply chain networks, leveraging heterogeneous graphs and temporal attention networks, achieving over 17.8% F1 improvement.
SAGE: An LLM-driven Self Reflective Agentic Framework for Fraud Detection
Introduces SAGE, the first end-to-end LLM-driven multi-agent framework for fraud detection, using a Data Diagnostic Tree and Markov decision process with natural-language gradients to optimize models under class imbalance. Experiments show significant F1 improvements over baselines across five datasets.
Multi-Stream Temporal Fusion for Financial Fraud Detection
Proposes the Multi-Stream Fraud Transformer (MSFT) for financial fraud detection, which independently encodes transaction, login, and risk event streams using Transformers and fuses them with time-aware positional encoding and gated fusion, achieving 0.9961 AUROC on a large dataset.