The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project will be to combat online trade in counterfeit and illicit goods. The project will integrate the results of a decade of academic research on anonymous online ("dark net") marketplaces and modeling of counterfeit pharmaceutical online sales with novel monitoring solutions for traditional e-commerce marketplaces. It will allow for the development and validation through pilot customer tests of an integrated platform for automated continuous data collection and analysis of the major players in the counterfeit and illicit goods online business. Through automation, the proposed technology should considerably reduce costs to brand protection managers (and law enforcement), allowing them to use their limited resources more effectively. This work should also help address some pressing economic and public health issues linked to the proliferation of counterfeits, such as counterfeit drugs.This Small Business Innovation Research (SBIR) Phase I project will demonstrate automation of many manual online counterfeiting monitoring activities. The project will also show that intuitive visual interfaces can help customers (law enforcement agencies, brand protection managers) have immediate access to higher-level objects more useful for investigative purposes. These higher-level objects include metrics on the amount of sales conducted by a specific entity, deduplication between vendors, or inventory clustering. To do so, the project will further develop automated classification and analysis using techniques that were prototyped in the research lab, scale these techniques up to a production environment to further minimize human intervention, and combine these techniques with novel algorithms developed for slightly different application cases (traditional e-commerce marketplaces).This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
