Analysis & Commentary:

VIRTUAL GOLD INC, NATIONAL SECURITY INITIATIVE BRIEFING
by Ed Colet

Citing critical need for proactive analysis of federal data, data mining pioneer announces initiative to address national security issues. Leading data mining expert and founder of Virtual Gold Inc, Inderpal Bhandari sees an urgent need for proactive analysis of federal data. Dr. Bhandari said, "I first noticed this when the New York Times did an analysis after the fact showing that early indications of the Ford-Explorer-Firestone-tire problem went undetected in a federal database. Recently, a similar analysis by CNN showed that early indications of security problems at Logan, Dulles, and Newark airports, went undetected in a federal database well before the September 11 tragedy. It is clear that the cost of missing these patterns is too high to be ignored".

Dr. Bhandari launched Virtual Gold's new initiative on MacInt, short for machine intelligence, a term well suited to denote the use of computers to provide cueing or early-warnings from data pertaining to national security. He sees a critical need for intelligence agencies to develop a sophisticated MacInt capability to go along with other intelligence capabilities such as SigInt (signal intelligence), ElInt (electronic intelligence) and HumInt (human intelligence). "Homeland security and intelligence agencies must build on the strength of technical data collection through the use of coordinated, proactive analysis of that data", he said. "Strategically, it is the only way forward".

Dr. Bhandari sees three major hurdles for homeland security and intelligence agencies as they try to become proficient at proactive analysis. First, they do not have an understanding of what it entails. Second, there are no off-the-shelf software packages available to help implement solutions to their unique set of problems. Third, unlike traditional intelligence capabilities, the MacInt infrastructure must extend to local, front-line response units. Virtual Gold's initiative will remove these obstacles by anticipating security needs and making suitable early-warning applications available to relevant organizations (including front-line organizations) before those needs arise.

Dr. Bhandari described how Virtual Gold's new initiative leads to proactive action. "We have a proprietary intelligent computer program currently under development that extrapolates future attack scenarios from patterns of past terrorist activities. We also have a proprietary software development platform that automatically introduces MacInt capability in off-the-shelf database and Internet software. We will use our extrapolative analysis to understand worst-case scenarios and use our development platform to rapidly develop intelligent computer programs to provide early warning of those scenarios. Then we will contact the relevant organizations to customize and deploy those programs".

For example, in applying its extrapolative logic to the recent wave of Anthrax-laced letters, Virtual Gold learned that instead of the targeted letters we see at present, a future scenario could be a mass mailing of Anthrax-laced cards, particularly during Christmas or other holiday. The law enforcement and public health response systems should not be overwhelmed by such a scenario, raising the issue of how the required infrastructure could be put in place before Christmas and holiday season.

In response, Virtual Gold is developing two MacInt software applications, the first tracks questionable mail nationwide and provides early-warning of contamination, while the second tracks initial symptoms nationwide and provides early-warning of exposure. Both applications are largely automated hence efficient. This will reduce the load on the public health and enforcement infrastructures.

Virtual Gold will have these applications functional by the end of this week -- less than two weeks after the scenario was extrapolated, indicated Thomas J. Martin, executive vice president. "These applications were created using our software development platform that automatically introduces MacInt capability in off-the-shelf database and internet software. We will confer with local law enforcement and health departments, the heads of corporate security in large enterprises, the Postal Service, Centers of Disease Control, to customize the solution to reflect their deeper understanding of the issue. Working proactively in this fashion, the applications can be fully deployed well before the start of the holiday season".

Interested parties (decision makers in national security) should read Dr. Bhandari's white paper, which describes a conceptual framework for MacInt. It is available at www.virtualgold.com/national-security. Then they should use the Web site to register for demonstrations of Virtual Gold's MacInt line of products to address scenarios in enforcement, surveillance, aviation safety, financial securities trading, bio-warfare and corporate security.

About Virtual Gold Inc

Virtual Gold Inc, www.virtualgold.com, is a leading next generation business intelligence and data mining software company. Former IBM scientist Dr. Inderpal Bhandari, one of the world's leading authorities on data mining and its timely application to real world problems, founded it in 1997. In addition to its MacInt line of products, Virtual Gold provides an integrated family of Web-based data mining software and solutions in the following fields: contact center, customer relationship management, enterprise resource planning, decision support systems, e-business, and sports and entertainment. The company is headquartered in Hartsdale, New York.

Ed Colet is the Acting Director of Research at Virtual Gold Inc., responsible for developing analytical methods for data mining and for investigating human factors and usability issues of business intelligence systems. At present, he is in the final stage of completing a doctoral dissertation in the Cognition and Perception program at New York University's Department of Psychology. Ed has also worked for IBM Research at the T.J. Watson Research Center. At IBM, Ed was a member of the group that developed Advanced Scout, the data mining application for NBA teams. His research interests focus on statistical methods and human factors.