How Smart Protection uses machine learning to thwart online piracy

Despite efforts to curb online piracy, some estimates suggest that pirate websites secured around 190 billion visits in 2018, affecting industries spanning TV, movies, music, publishing, and software. According to a recent report by the U.S. Chamber of Commerce, digital video piracy alone results in nearly $30 billion in lost revenue annually in the U.S. Against this backdrop, Smart Protection is working to help brands and rightsholders identify online hubs that host illegal streams, downloads, and other types of content infringement. Founded out of Madrid, Spain in 2015, Smart Protection uses machine learning and big data processing -- in concert with natural language processing (NLP), computer vision, keyword searches, and more -- to find the hubs hosting piracy and counterfeit content. By scanning the web, Smart Protection effectively builds a huge database of URLs, and it then applies its various machine learning algorithms that have been tailored to each content type and classifies the URLs based on the likelihood that they are hosting illicit content. "Typically, we eliminate approximately 98% [of the URLs], and it is from the remaining 2% that counterfeits, piracy, or brand abuse are hosted," Javier Perea, CEO and cofounder of Smart Protection, told VentureBeat.