Abstract
It is a critical mission for financial service providers to discover fraudulent borrowers in a supply chain. The borrowers’ transactions in an
ongoing business are inspected to support the providers’ decision on whether to lend the money. Considering multiple participants in a supply chain business, the borrowers may use sophisticated tricks to cheat, making fraud detection
challenging. In this work, we propose a multitask learning framework, MultiFraud, for complex fraud detection with reasonable explanation. The heterogeneous information from multi-view around the entities is leveraged in the detection framework based on heterogeneous graph neural networks. MultiFraud enables multiple domains to share embeddings and enhance modeling capabilities for fraud detection. The developed explainer provides comprehensive explanations across multiple graphs. Experimental results on five datasets demonstrate the framework’s effectiveness in fraud detection and explanation across domains.
© 2023, Elsevier. This is an author produced version of a paper published in Information Systems uploaded in accordance with the publisher’s self- archiving policy. The final published version (version of record) is available online at the link. Some minor differences between this version and the final published version may remain. We suggest you refer to the final published version should you wish to cite from it.
ongoing business are inspected to support the providers’ decision on whether to lend the money. Considering multiple participants in a supply chain business, the borrowers may use sophisticated tricks to cheat, making fraud detection
challenging. In this work, we propose a multitask learning framework, MultiFraud, for complex fraud detection with reasonable explanation. The heterogeneous information from multi-view around the entities is leveraged in the detection framework based on heterogeneous graph neural networks. MultiFraud enables multiple domains to share embeddings and enhance modeling capabilities for fraud detection. The developed explainer provides comprehensive explanations across multiple graphs. Experimental results on five datasets demonstrate the framework’s effectiveness in fraud detection and explanation across domains.
© 2023, Elsevier. This is an author produced version of a paper published in Information Systems uploaded in accordance with the publisher’s self- archiving policy. The final published version (version of record) is available online at the link. Some minor differences between this version and the final published version may remain. We suggest you refer to the final published version should you wish to cite from it.
| Original language | English |
|---|---|
| Journal | information systems |
| Publication status | Published - 10 Dec 2023 |