We have developed visual analysis methods to investigate hundreds of thousands or more bank transactions over extended periods of time. Transactions are clustered and reclustered according to their similarities and then explored for patterns of keywords, distribution within and between clusters, amount of activity or amount of money transferred, and other factors. Multiple interlinked views are maintained so that users can rapidly navigate from overviews to particular views of keyword correlations, transactional activity, or even the details of specific transactions. These methods are being applied to investigations of wireless transfer transactions for possible money laundering. The process here is similar in several ways to intelligence analysis. The tools are general and can be applied to other types of transactional analysis over time.
The figure shows some interlinked views. As the user moves the mouse in the left panel, transaction activity over time and selected keywords are highlighted in the middle panel. The time period for the middle panel is one year, and the bright red dots indicate that selected keywords appear at that time in transaction clusters selected. The right panel shows how the user can zoom in to selected clusters and get detailed views of distribution of keywords within clusters. This work is in conjunction with the Bank of America and is led by Robert Kosara, Jing Yang, and Remco Chang.