The Financial Crimes Enforcement Network AI System (FAIS) Identifying Potential Money Laundering from Reports of Large Cash Transactions

CEN) AI system (FAIS) links and evaluates reports of large cash transactions to identify potential money laundering. The objective of FAIS is to discover previously unknown, potentially high-value leads for possible investigation. FAIS integrates intelligent human and software agents in a cooperative discovery task on a very large data space. It is a complex system incorporating several aspects of AI technology, including rule-based reasoning and a blackboard. FAIS consists of an underlying database (that functions as a blackboard), a graphic user interface, and several preprocessing and analysis modules. FAIS has been in operation at FINCEN since March 1993; a dedicated group of analysts process approximately 200,000 transactions a week, during which time over 400 investigative support reports corresponding to over $1 billion in potential laundered funds were developed. FAIS’s unique analytic power arises primarily from a change in view of the underlying data from a transaction-oriented perspective to a subject-oriented (that is, person or organization) perspective. The Financial Crimes Enforcement Network (FINCEN) is a relatively new agency (founded in 1990) of the U.S. Treasury Department whose mission is to establish, oversee, and implement policies to prevent and detect money laundering in support of federal, state, and local law enforcement. A key data source available to FINCEN is reports of large cash transactions made to the Treasury according to terms of the Bank Secrecy Act.2 FINCEN has developed a system, called the FINCEN AI System (FAIS), which links and evaluates all reported transactions for indications of suspicious activity characteristic of money laundering, with the objective of identifying previously unknown, potentially highvalue leads for follow-up investigation and, if warranted, prosecution (Wall Street Journal 1993). FAIS integrates intelligent software and human agents in a cooperative discovery task on a very large data space. It is a complex system incorporating several aspects of AI technology, including rule-based reasoning and a blackboard. FAIS consists of an underlying database, a graphic user interface, and several preprocessing and analysis modules. The database functions as a blackboard and is implemented in SYBASE. The graphic user interface is implemented in Neuron Data’s OPEN INTERFACE. The suspiciousness evaluation module is a rule-based reasoner implemented in Neuron Data’s NEXPERT OBJECT (now called Articles