January 19, 2011 – In an era where margins are tight and budgets are tighter, insurance companies and brokers can ill afford the losses that inevitably come as a result of fraud, yet there is no doubt that such crimes will continue.

We soldier on, hoping that technology will somehow come up with something to give us hope, and it appears that a new system developed by the Management Group of the Universitat Politècnica de Catalunya (DAMA-UPC) may do just that.

The DAMA-UPC group has designed a system for exploring information on networks or graphs that can complement Internet search engines, and is of particular interest in areas related to social media, the Internet, biomedicine, fraud detection, education and other areas, says a report in Science Daily.

According to Josep Lluís Larriba, director of DAMA-UPC, the technology can be used to extract information from WikiLeaks from two perspectives:

  1. To obtain generic indicators that provide information on whether the data network has the features of a social network, and whether communities of data are created that can provide relevant information; and
  2. To use the documents hosted on the website to analyze how a topic evolves over time, how a person or a group relates to different topics and how the documents themselves interrelate.

While that sounds like a lot of manipulation of a lot of data, the bottom line is that the new DEX technology patented by the UPC can be used to explore large volumes of networked data, says the Science Daily report. The system offers high-speed processing, configurable data entry from multiple sources, and the management of networks with billions of nodes and connections from a desktop PC.
Users can quickly and easily identify interrelated records by formulating queries based on simple values such as names and keywords — something that was only possible to a limited extent until now, the report notes. In what was the first major application of DEX, the Notary Certification Agency (ANCERT) used the technology to detect fraud in real estate transactions and the Catalan Institute of Oncology is using it to study the evolution of cancer in Catalonia.

Looking at these encouraging results from an insurance point of view, not only can we hope to have a sophisticated weapon in the fight against fraud, but we also can expect to gather information that will impact health insurance decisions. And since — as noted here in other postings — much cyber-crime activity is focused on social networks, the system’s ability to comb those networks for suspicious patterns will be a welcome feature.

To be sure, this technology is in its early stages. We should be encouraged, however, by the obvious fact that technological developments tend to mature at breakneck speed. Let’s hope that our Catalan friends have great success in exporting this technology to insurance and other industries in which fraud, crime and lack of information may be critical problems.

This article originally appeared on Insurance Networking News.

Register or login for access to this item and much more

All Information Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access