Abstract: High resource constraints and the covert nature of sex trafficking provide significant barriers to developing data-driven innovations that inform law enforcement investigations and trials. We leverage massive deep web data (collected globally from leading adult services websites) in tandem with a novel machine learning framework to unmask sex-trafficking recruitment-to-sales pathways, thereby providing the first global network view of sex trafficking supply chains. This allows us to identify popular recruitment-to-sales trafficking routes of criminal organizations, different approaches used to recruit victims, and regional variations in recruitment vs. sales pressure. Our methods can inform counter-trafficking efforts for law enforcement, helping agencies extract more economic value from their data-driven innovations. This work is conducted in collaboration with Uncharted, a company providing software to law enforcement for visualizing patterns in deep web data.