Multi-Relational Graph Representation Learning for Financial Statement Fraud Detection
Financial statement fraud refers to malicious manipulations of financial data in listed companies’ annual statements. Traditional machine learning approaches focus on individual companies, overlooking the interactive relationships among companies that are crucial for identifying fraud patterns. More...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2024-09-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2024.9020013 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832572873139552256 |
|---|---|
| author | Chenxu Wang Mengqin Wang Xiaoguang Wang Luyue Zhang Yi Long |
| author_facet | Chenxu Wang Mengqin Wang Xiaoguang Wang Luyue Zhang Yi Long |
| author_sort | Chenxu Wang |
| collection | DOAJ |
| description | Financial statement fraud refers to malicious manipulations of financial data in listed companies’ annual statements. Traditional machine learning approaches focus on individual companies, overlooking the interactive relationships among companies that are crucial for identifying fraud patterns. Moreover, fraud detection is a typical imbalanced binary classification task with normal samples outnumbering fraud ones. In this paper, we propose a multi-relational graph convolutional network, named FraudGCN, for detecting financial statement fraud. A multi-relational graph is constructed to integrate industrial, supply chain, and accounting-sharing relationships, effectively encapsulating the multidimensional and complex interactions among companies. We then develop a multi-relational graph convolutional network to aggregate information within each relationship and employ an attention mechanism to fuse information across multiple relationships. The attention mechanism enables the model to distinguish the importance of different relationships, thereby aggregating more useful information from key relationships. To alleviate the class imbalance problem, we present a diffusion-based under-sampling strategy that strategically selects key nodes globally for model training. We also employ focal loss to assign greater weights to harder-to-classify minority samples. We build a real-world dataset from the annual financial statement of listed companies in China. The experimental results show that FraudGCN achieves an improvement of 3.15% in Macro-recall, 3.36% in Macro-F1, and 3.86% in GMean compared to the second-best method. The dataset and codes are publicly available at: https://github.com/XNetLab/MRG-for-Finance. |
| format | Article |
| id | doaj-art-4abe6e7fdae4473ca58e85035de22299 |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-4abe6e7fdae4473ca58e85035de222992025-02-02T06:29:08ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-09-017392094110.26599/BDMA.2024.9020013Multi-Relational Graph Representation Learning for Financial Statement Fraud DetectionChenxu Wang0Mengqin Wang1Xiaoguang Wang2Luyue Zhang3Yi Long4School of Software Engineering, and also with MoE Key Lab of Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an 710049, ChinaSchool of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaSchool of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaSchool of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaShenzhen Finance Institute, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen 518026, ChinaFinancial statement fraud refers to malicious manipulations of financial data in listed companies’ annual statements. Traditional machine learning approaches focus on individual companies, overlooking the interactive relationships among companies that are crucial for identifying fraud patterns. Moreover, fraud detection is a typical imbalanced binary classification task with normal samples outnumbering fraud ones. In this paper, we propose a multi-relational graph convolutional network, named FraudGCN, for detecting financial statement fraud. A multi-relational graph is constructed to integrate industrial, supply chain, and accounting-sharing relationships, effectively encapsulating the multidimensional and complex interactions among companies. We then develop a multi-relational graph convolutional network to aggregate information within each relationship and employ an attention mechanism to fuse information across multiple relationships. The attention mechanism enables the model to distinguish the importance of different relationships, thereby aggregating more useful information from key relationships. To alleviate the class imbalance problem, we present a diffusion-based under-sampling strategy that strategically selects key nodes globally for model training. We also employ focal loss to assign greater weights to harder-to-classify minority samples. We build a real-world dataset from the annual financial statement of listed companies in China. The experimental results show that FraudGCN achieves an improvement of 3.15% in Macro-recall, 3.36% in Macro-F1, and 3.86% in GMean compared to the second-best method. The dataset and codes are publicly available at: https://github.com/XNetLab/MRG-for-Finance.https://www.sciopen.com/article/10.26599/BDMA.2024.9020013financial statement fraudclass imbalancegraph neural networks (gnn)multi-relational graphs |
| spellingShingle | Chenxu Wang Mengqin Wang Xiaoguang Wang Luyue Zhang Yi Long Multi-Relational Graph Representation Learning for Financial Statement Fraud Detection Big Data Mining and Analytics financial statement fraud class imbalance graph neural networks (gnn) multi-relational graphs |
| title | Multi-Relational Graph Representation Learning for Financial Statement Fraud Detection |
| title_full | Multi-Relational Graph Representation Learning for Financial Statement Fraud Detection |
| title_fullStr | Multi-Relational Graph Representation Learning for Financial Statement Fraud Detection |
| title_full_unstemmed | Multi-Relational Graph Representation Learning for Financial Statement Fraud Detection |
| title_short | Multi-Relational Graph Representation Learning for Financial Statement Fraud Detection |
| title_sort | multi relational graph representation learning for financial statement fraud detection |
| topic | financial statement fraud class imbalance graph neural networks (gnn) multi-relational graphs |
| url | https://www.sciopen.com/article/10.26599/BDMA.2024.9020013 |
| work_keys_str_mv | AT chenxuwang multirelationalgraphrepresentationlearningforfinancialstatementfrauddetection AT mengqinwang multirelationalgraphrepresentationlearningforfinancialstatementfrauddetection AT xiaoguangwang multirelationalgraphrepresentationlearningforfinancialstatementfrauddetection AT luyuezhang multirelationalgraphrepresentationlearningforfinancialstatementfrauddetection AT yilong multirelationalgraphrepresentationlearningforfinancialstatementfrauddetection |