Anti-money Laundering (AML) Research: A System for Identification and Multi-classification

• Published in: Web Information Systems and Applications Vol. 11817; pp. 169 - 175
• Main Authors: Feng, Yixuan, Li, Chao, Wang, Yun, Wang, Jian, Zhang, Guigang, Xing, Chunxiao, Li, Zhenxing, Lian, Zengshen
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2019; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: AML; Classification; Features extraction
• ISBN: 9783030309510; 3030309517
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-30952-7_19

Anti-money laundering (AML) is of great significance for the integrity of financial system in modern society because of the huge amounts of money involved in and close relationships with other types of crimes. The typical AML system includes FinCEN for America which began in 1993 and AUSTRAC for Australia. This paper aims to develop a suspicious behavior detection and categorization system based on money transaction data collected from the simulator called Paysim. For preparation work, in order to facilitate crimes classification in the second step, the associated criminal activities were divided into five categories according to their different characteristics shown in the money transaction process. Then on the basis of the transaction data, a user profile was created and new features concerning both individual parties and network effect were extracted from the profile. With combined features, two models were developed for detection and classification using supervised learning methods separately. The results show good accuracy and recall rate which are most valued in reality. Meanwhile, the models display good robustness to further adjustment for practical use. Finally two models were connected in series, and the result shows a relatively good overall performance and verifies the feasibility of the system, as it provides more choices for users to decide which model (or both) to apply according to different situations in practice.