Article: GraphBiGRU model for anti-money laundering based on preference-based reinforcement learning via the label filtering loop mechanism Journal: International Journal of Computational Science and Engineering (IJCSE) 2025 Vol.28 No.5 pp.530 - 542 Abstract: Anti-money laundering (AML) in Bitcoin transactions remains challenging since Bitcoin data has a complex graph structure and sequential nature, with many unknown labels and an imbalanced distribution of licit and illicit transactions. To address these challenging issues, we propose a novel reinforcement learning-based GraphBiGRU model via the label filtering loop mechanism to detect illicit transactions in the Bitcoin blockchain. Specifically, we first constructed the GraphBiGRU network to learn the graph structure and temporal information of Bitcoin data. Then, we introduced the label filtering loop mechanism, which encouraged the GraphBiGRU to select reliable pseudo-labelled samples that reduced data noise interference. In addition, we investigated a preference-based reinforcement learning strategy that enabled the GraphBiGRU to better identify illicit transactions, thereby improving performance on imbalanced datasets. Finally, we conducted experiments on the Elliptic dataset, demonstrating that our method achieved state-of-the-art performance, especially with a limited labelled dataset. Inderscience Publishers - linking academia, business and industry through research

Title: GraphBiGRU model for anti-money laundering based on preference-based reinforcement learning via the label filtering loop mechanism

Authors: Meng Li; Xinqiao Su; Lu Jia; Rongbo You

Addresses: School of Statistic and Mathematics, Hebei University of Economics and Business, Shijiazhuang, China ' School of Statistic and Mathematics, Hebei University of Economics and Business, Shijiazhuang, China ' School of Statistic and Mathematics, Hebei University of Economics and Business, Shijiazhuang, China ' School of Statistic and Mathematics, Hebei University of Economics and Business, Shijiazhuang, China

Abstract: Anti-money laundering (AML) in Bitcoin transactions remains challenging since Bitcoin data has a complex graph structure and sequential nature, with many unknown labels and an imbalanced distribution of licit and illicit transactions. To address these challenging issues, we propose a novel reinforcement learning-based GraphBiGRU model via the label filtering loop mechanism to detect illicit transactions in the Bitcoin blockchain. Specifically, we first constructed the GraphBiGRU network to learn the graph structure and temporal information of Bitcoin data. Then, we introduced the label filtering loop mechanism, which encouraged the GraphBiGRU to select reliable pseudo-labelled samples that reduced data noise interference. In addition, we investigated a preference-based reinforcement learning strategy that enabled the GraphBiGRU to better identify illicit transactions, thereby improving performance on imbalanced datasets. Finally, we conducted experiments on the Elliptic dataset, demonstrating that our method achieved state-of-the-art performance, especially with a limited labelled dataset.

Keywords: anti-money laundering; AML; illicit transactions; GraphBiGRU; label filtering loop mechanism; pseudo-labelled samples; preference-based reinforcement learning; Elliptic dataset.

DOI: 10.1504/IJCSE.2025.148738

International Journal of Computational Science and Engineering, 2025 Vol.28 No.5, pp.530 - 542

Received: 12 Jun 2024
Accepted: 06 Oct 2024
Published online: 22 Sep 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: GraphBiGRU model for anti-money laundering based on preference-based reinforcement learning via the label filtering loop mechanism

Keep up-to-date