Attention-based Conditional Random Field for Financial Fraud Detection

Wang, Xiaoguang; Wang, Chenxu; Zhang, Luyue; Wang, Xiaole; Wang, Mengqin; Liu, Huanlong; Qin, Tao

doi:10.24963/ijcai.2025/870

Attention-based Conditional Random Field for Financial Fraud Detection

Xiaoguang Wang, Chenxu Wang, Luyue Zhang, Xiaole Wang, Mengqin Wang, Huanlong Liu, Tao Qin

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 7822-7830.

https://doi.org/10.24963/ijcai.2025/870

Keywords

Knowledge Representation and Reasoning: KRR: Applications
Data Mining: DM: Anomaly/outlier detection
Multidisciplinary Topics and Applications: MTA: Finance
Machine Learning: ML: Attention models

Abstract

Financial fraud detection is critical for market transparency and regulatory compliance. Existing methods often ignore the temporal patterns in financial data, which are essential for understanding dynamic financial behaviors and detecting fraud. Moreover, they also treat companies as independent entities, overlooking the valuable interrelationships. To address these issues, we propose ACRF-RNN, a Recurrent Neural Network (RNN) with Attention-based Conditional Random Field (CRF) for fraud detection. Specifically, we use an RNN with a sliding window to capture temporal dependencies from historical data, and an attention-based CRF feature transformer to model inter-company relationships. This transforms raw financial data into optimized features, fed into a multi-layer perceptron for classification. Besides, we also use the focal loss to alleviate the class imbalance problem caused by rare fraudulent cases. This work presents a novel real-world dataset to evaluate the performance of ACRF-RNN. Extensive experiments show that ACRF-RNN outperforms the state-of-the-art methods by 15.28% in KS and 4.04% in Recall.

Data and code are available at: https://github.com/XNetLab/ACRF-RNN.git.

Xiaoguang Wang, Chenxu Wang, Luyue Zhang, Xiaole Wang, Mengqin Wang, Huanlong Liu, and Tao Qin. 2025. Attention-based Conditional Random Field for Financial Fraud Detection. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 7822–7830. https://doi.org/10.24963/ijcai.2025/870

@inproceedings{ijcai2025p870,
  title     = {Attention-based Conditional Random Field for Financial Fraud Detection},
  author    = {Wang, Xiaoguang and Wang, Chenxu and Zhang, Luyue and Wang, Xiaole and Wang, Mengqin and Liu, Huanlong and Qin, Tao},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {7822--7830},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/870},
  url       = {https://doi.org/10.24963/ijcai.2025/870},
}

TY  - CPAPER
TI  - Attention-based Conditional Random Field for Financial Fraud Detection
AU  - Wang, Xiaoguang
AU  - Wang, Chenxu
AU  - Zhang, Luyue
AU  - Wang, Xiaole
AU  - Wang, Mengqin
AU  - Liu, Huanlong
AU  - Qin, Tao
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 7822
EP  - 7830
DO  - 10.24963/ijcai.2025/870
UR  - https://doi.org/10.24963/ijcai.2025/870
ER  -