SBIR Phase I: Software to Aggregate, Correlate, Analyze and Trend data for Knowledge Management in Decision Making

This Small Business Innovation Research Phase I project evaluates the feasibility of correlating quantitative internet ""chatter"" to relevant business metrics for use in decision making. This product will aggregate and longitudinally analyze information from the Internet in order to identify trends and statistical correlations to relevant business metrics. The approach offers a solution to a problem most companies face, that of the inability to comprehend and react to the immense quantity of data available online related to their products/services and corporate reputation. In order to confirm feasibility, the research objectives for the project start with successfully collecting Internet ""chatter"" related to upcoming movie releases, and collecting box office and DVD sales metrics over the course of several months. After the data is collected, detailed statistical analysis will be performed to determine if a correlation exists between the two data sets. Finally, the commercial viability for decision making support based on the resulting output will be determined. Vyante's vision includes advanced functionality for semantic and contextual analysis, emergent trend identification, and enablement of predictive modeling. Broader commercial impact beyond the ability to better understand the relevance of ""chatter"" to business metrics such as sales can be developed. For instance, as a risk monitoring tool could be developed which is especially important in the pharmaceutical and medical device industries where liability for an issue can increase by millions of dollars per day. The ability to react more quickly can prevent financial catastrophe; Vioxx and Guidant provide recent high-profile examples. The approach offers a consolidated view into the ""voice to the customer"", allowing a better understanding of general public sentiment about topics ranging from new products to corporate initiatives and political issues. The underlying technology incorporates a new method for aggregating massive amounts of data across thousands of data sources and applies existing statistical methods to create complex statistical models allowing for scientifically relevant information to be used for decision making purposes.