| Summary: | In recent years, stakeholder economic crime behaviors such as illegal pyramid schemes, illegal fund raising and money laundering despite repeated prohibitions, makes the research of anomaly detection in financial transaction network has gradually attracted the attention of researchers. The way how to fund flow between bank accounts in an illegal organization implies the relationship structure of their members. Firstly, a directed weighted transaction network model was built on the basis of the transaction characteristics. Then, combining with the local topology structure of the built transaction network of the accounts, two kinds of core nodes of the organization, including black hole nodes and star nodes, were defined. By analyzing the relationship between those two kinds nodes, an organization discovery algorithm of combining “black hole and star nodes” based on spanning subgraph was proposed. Experiments on real bank accounts transaction network containing illegal pyramid scheme organizations show the effectiveness of the algorithm in discovering the specific tree organization structure.
|
|---|