Software Suite for Identifying Suspicious Individuals

Traditional data mining has focused on known relationships between people and transactions. However, such methodologies fail when trying to identify key associates in situations such as advanced money laundering schemes and terrorist organizations.

The US Air Force Research Laboratory Information Directorate (AFRL/RI) has introduced a new paradigm called Uni-Parity Data Community Generation (UDCG) and developed Link Discovery based on Correlation Analysis (LDCA), a new methodology to discover social groups. The purpose is to greatly reduce the time required for analysts to discover and analyze communities of interest and key figures where explicit relationships are not obvious.

AFRL/RI has developed and tested a suite of mathematical models and software to extract pertinent data from large data sets (paper, electronic, and online), analyze complex data sets, determine key groups within those datasets, and provide visualization tools. Key developments include a name resolution system for data extraction and a mathematical approach that is insensitive to transaction errors. The AFRL/RI system has successfully validated using actual data from two large financial frauds: 1) A $45 million money laundering and Ponzi scheme based in the US, and 2) the Enron scandal.

BENEFITS:

• Robust: Core algorithms are simple and insensitive to errors
• Efficient: Suite of tools and algorithms greatly reduces the time and energy required by analysts to focus in on core data and identify potential key members of a target group
• Proven on Real World Data: AFRL/RI’s system was honed with complex information from two massive financial fraud cases using paper, electronic, and online datasets