Application of the CURE Algorithm in Identifying Suspicious Financial Transactions

摘要：

In China anti-money laundering! an fundamental task is to combine data mining (DM) methods with financial. knowledge to identify suspicious financial transactions (SFT). As an important data mining method, clustering analysis can be conducted to find the information distribution hidden in data, but to apply it to identify SFT, there are more issues like vulnerably abnormal data and so on. The algorithm of clustering using representatives CURE) is efficient for large database and suitable for financial DM, using random sampling and partitioning clustering, with good scalability. This paper presents an improved CURE algorithm to search for unusual clients with SFT, and experiments on it, the result of which shows that the method can provide efficient identification of SFT.

关键词： dalta mining suspicious financial transactions clustering analysis CURE algorithm

作者: Zhang Cheng-hu Zhao Yan Zhao Xiao-hu

作者单位: School of Economic & Finance Xian Jiaotong University Xian, China Shaanxi Branch of the State Administration of Foreign Exchange Xian, China

会议类型: 国际会议

会议名称: 2011 International Conference on Information and Industrial Electronics(2011年信息与工业电子国际会议 ICIIE 2011)

会议地点: 成都

会议语种:英文

页码: 574-577

在线出版日期: 2011-01-14（万方平台首次上网日期，不代表论文的发表时间）