Open AccessIdentification of money laundering accounts based on weighted capital flow network
Author(s) -
Jian Xiong,
Haifeng Zhong
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1629/1/012023
Subject(s) - money laundering , database transaction , capital (architecture) , computer science , key (lock) , identification (biology) , node (physics) , flow (mathematics) , ranking (information retrieval) , monetary economics , business , computer security , economics , finance , engineering , artificial intelligence , mathematics , database , botany , geometry , archaeology , structural engineering , biology , history
Money laundering is an activity of transferring money through fraud and concealment. And its behaviour is different from normal transaction. The key to identifying money laundering crime is to find illegal account from massive capital flow data. The paper studies a method to identify the money laundering nodes by constructing the structural features of the capital flow network. According to the characteristics, we define the calculation methods of node outgoing, incoming and connectivity in the capital flow network, and identify the key nodes. The experimental results show that this method can find abnormal account from large-scale capital transaction data. Although the accuracy needs to be improved, it can help extract evidence of money laundering by ranking the weight and analyzing the capital flow from high-weight account.