Researchers at the Department of Energy’s Pacific Northwest National Laboratory (PNNL) have developed new software that helps identify anomalies in complex financial data, in hopes of detecting problematic financial trends that jeopardize U.S. and global financial systems. It’s a great example of the kinds of research opportunities at the intersection of computer science and finance.

From the official DoE press release:

Identifying atypical 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 downward fall. Recognizing such anomalous information can also help regulators, investors and advisors better manage their investment and savings portfolios.

 

Now, new analytical software developed by Battelle researchers based [at PNNL] can do just that…

 

In a demonstration of this technology, the Battelle-developed Anomalator™ software recently picked out the atypically stable and positive returns reported by disgraced financier Bernard Madoff as an anomaly among hundreds of funds. He is now serving a 150-year prison sentence for scamming investors out of as much as $65 billion in a Ponzi scheme that spanned at least 20 years. Unfortunately, Madoff’s fraud was concealed for more than 15 years. The use of this sophisticated anomaly-detection and visualization tool could have exposed Madoff early on, and can help expose future scandals, its inventors say…

 

Traditional financial analysis reports either provide a list of numbers or a simple line graph to represent the value of just one investment over time. The Anomalator™ is unique in its ability to identify unusual trends in complex financial data and graphically show how it compares with larger datasets.

So how does it work? Find out after the jump…

» Read more: Pinpointing Anomalies in Complex Financial Data