Deep learning-based online counterfeit-seller detection
Ming Cheung, James Pei Man She, Lufi Liu · 2018
With the advancement of social media and mobile technology, any smartphone users can easily become a seller on social media and e-commerce platforms, such as Instagram and Carousell. A seller shows images of their products, and annotates their images with suitable tags that can be searched easily by others. Those images could be taken by the seller, or they could use images shared by other sellers. Their customers can receive the information by following them or searching them with tags. Among sellers, some sell counterfeit goods, and these sellers may use different tags and language, which make detecting them a difficult task. This paper proposes a framework to detect counterfeit sellers by discovering connections among sellers from their shared images using deep learning. Based on 60,018 and 259,926 images from 138 and 185 sellers on Instagram and Carousell, it is proven that the proposed framework can detect counterfeit sellers. To the best of our knowledge, this is the first work to detect online counterfeit sellers from their shared images.