Semi-automatic identification of counterfeit offers in online shopping platforms

Product counterfeiting in online platforms is an increasingly serious problem causing estimated losses of billions of dollars every year. The huge number of online shops and offered products call for largely automated approaches to identify likely counterfeits, although identifying counterfeits is very difficult even for humans. The authors propose the adoption of a semiautomatic workflow to inspect product offers in online platforms and to determine likely counterfeit offers based on different criteria. Such suspicious offers are to be presented to a domain expert for manual verification. The workflow includes steps to match and cluster similar product offers, and to assess the counterfeit suspiciousness based on different criteria. The goal is to support the periodic identification of many counterfeit offers with a limited amount of manual effort. The authors also present a preliminary evaluation of the proposed approach on a case study using the eBay platform.