Generative Dynamic Graph Representation Learning for Conspiracy Spoofing Detection

2025-10-07

AI Summary

Addressing key challenges in collusive fraud detection within financial transactions—including difficulty in modeling dynamic relationships, weak capture of irregular temporal patterns, and neglect of topological context for isolated nodes—this paper proposes a generative dynamic graph model. The method integrates neural ordinary differential equations (ODEs) with gated recurrent units (GRUs) to model continuous-time evolution, combines heterogeneous information aggregation with dynamic graph representation learning to construct a generative latent space, and incorporates a pseudo-labeling mechanism to enhance relational reasoning under weak supervision. Evaluated on multiple real-world financial datasets, the approach achieves significant improvements in collusive fraud identification accuracy, with an average AUC gain of 4.2%. Furthermore, the model has been deployed across major global financial markets, demonstrating strong robustness and practical applicability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Spoofing detection in financial trading is crucial, especially for identifying complex behaviors such as conspiracy spoofing. Traditional machine-learning approaches primarily focus on isolated node features, often overlooking the broader context of interconnected nodes. Graph-based techniques, particularly Graph Neural Networks (GNNs), have advanced the field by leveraging relational information effectively. However, in real-world spoofing detection datasets, trading behaviors exhibit dynamic, irregular patterns. Existing spoofing detection methods, though effective in some scenarios, struggle to capture the complexity of dynamic and diverse, evolving inter-node relationships. To address these challenges, we propose a novel framework called the Generative Dynamic Graph Model (GDGM), which models dynamic trading behaviors and the relationships among nodes to learn representations for conspiracy spoofing detection. Specifically, our approach incorporates the generative dynamic latent space to capture the temporal patterns and evolving market conditions. Raw trading data is first converted into time-stamped sequences. Then we model trading behaviors using the neural ordinary differential equations and gated recurrent units, to generate the representation incorporating temporal dynamics of spoofing patterns. Furthermore, pseudo-label generation and heterogeneous aggregation techniques are employed to gather relevant information and enhance the detection performance for conspiratorial spoofing behaviors. Experiments conducted on spoofing detection datasets demonstrate that our approach outperforms state-of-the-art models in detection accuracy. Additionally, our spoofing detection system has been successfully deployed in one of the largest global trading markets, further validating the practical applicability and performance of the proposed method.

Problem

• Detecting complex conspiracy spoofing in financial trading systems
• Capturing dynamic irregular trading patterns in evolving markets
• Modeling temporal relationships between interconnected trading nodes

Innovation

• Generative Dynamic Graph Model for dynamic trading behaviors
• Neural ODEs and GRUs capture temporal spoofing patterns
• Pseudo-label generation and heterogeneous aggregation enhance detection