Follow Datanami:
October 31, 2011

Research Spawns “Anomalator” to Fight Financial Collapse

Datanami Staff

Pacific Northwest National Laboratory, a Battelle-operated DOE research center that focuses on problematic issues in energy, environmental science and national security, released news that emerging analytics software from Battelle researchers can work toward preventing financial crises.

While there are no algorithms that can prevent bad decision-making on the part of financial services professionals, the lab says their new software does aim to detect the prevalence of problematic investments before they reach critical mass.

The software, called Anomalator, uses a range of algorithms to look for inconsistencies across large datasets and across people, funds and time. The output is a line graph that measures movement across a number of factors.

For instance, in a recent demo, the software was able to backtrack to spot atypical stable and positive returns as reported by Bernard Madoff across a series of hundreds of funds. The team behind the software says that using this “sophisticated anomaly-detection and visualization tool could have exposed Madoff early on and can help expose future scandals.”

The software’s creators say that these algorithms go far beyond traditional methods to track the same problems in financial data. They say that previous forms of trend tracking would only provide a list of numbers or a simplistic line graph that monitored the evolution of investments over time. They say that “the anomalator is unique in its ability to identify unusual trends in complex financial data and graphically shows how it compares to larger datasets.”

According to representatives from Pacific Northwest Laboratory, “Identifying atyptical information in financial data early could help identify problematic financial trends such as the systemic risk that recently put the U.S. and global financial systems in a financial downfall.” They say that seeing inconsistencies at an early stage will also allow for better portfolio management on the part of regulation officials and investment or financial advisors.

The software has been licensed to V-Indicator Analytics, a Spokane-based research, analytics and visualization firm. While the company’s site is still a mere “something cool is coming soon” page and details about V-Indicator are scant, Sheppard did provide a brief description of his company. He says that V-Indicator’s technology will represent “new ways to process, rank, view, analyze, visualize and understand patterns derived from data—exposing variations, anomalies and outliers in complex datasets that are often otherwise obscure when expressed only in numbers and/or words.”

According to a release this week, the company’s president, Burton “Bud” Sheppard knew of the lab’s track record for creating advanced applications for homeland security and approached Battelle about developing the software. According to Battelle, they put up their “own private technology maturation funds to finance the development and then granted a license to V-Indicator to market the software for use in the financial services industry.”