We present a data mining approach for profiling bank clients in order to support the process of detection of antimoney laundering operations. We first present the overall system architecture, and then focus on the relevant component for this paper. We detail the experiments performed on real world data from a financial institution, which allowed us to group clients in clusters and then generate a set of classification rules. We discuss the relevance of the founded client profiles and of the generated classification rules. According to the defined overall agent-based architecture, these rules will be incorporated in the knowledge base of the intelligent agents responsible for the signaling of suspicious transactions.
Resumo: Branqueamento de capitais é um crime que possibilita o financiamento de outros crimes, por isso ele é importante para as organizações criminosas e seu combate é motivo de mobilização das nações do mundo inteiro. O processo de anti-branqueamento de capitais não evoluiu como esperado pois tem priorizado a sinalização de transações suspeitas. O crescente aumento no volume de transações tem sobrecarregado o indispensável trabalho humano de avaliação final das sinalizações. Este artigo apresenta um sistema multiagente que objetiva ir além da captura de transações suspeitas, buscando auxiliar o especialista humano na análise das suspeições. Os agentes criados utilizam técnicas de data mining para criação de perfis de comportamento transacional; aplicam as regras obtidas no aprendizado em conjunto com regras especificas baseadas em aspectos legais e nos perfis criados para captura de transações suspeitas; e analisam estas transações sinalizadas indicando ao especialista humano aquelas que necessitam de análise mais detalhada.Palavras-chave: Sistemas multiagente; agentes inteligentes; data mining; antibranqueamento de capitais.
A Multi-Agent System in the Combat Against Money LaunderingAbstract: Money laundering is a crime that makes it possible to finance other crimes, for this reason, it is important for criminal organizations and their combat is prioritized by nations around the world. The anti-money laundering process has not evolved as expected because it has prioritized only the signaling of suspicious transactions. The constant increasing in the volume of transactions has overloaded the indispensable human work of final evaluation of the suspicions. This article presents a multiagent system that aims to go beyond the capture of suspicious transactions, seeking to assist the human expert in the analysis of suspicions. The agents created use data mining techniques to create transactional behavioral profiles; apply rules generated in learning process in conjunction with specific rules based on legal aspects and profiles created to capture suspicious transactions; and analyze these suspicious transactions indicating to the human expert those that require more detailed analysis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.