Researchers from Leiden University have developed a way to predict which sellers will be successful on illegal online marketplaces, which could help police track down bigwigs on the dark web, a hidden part of the internet.
Drugs, weapons, hacked personal data, and child abuse images are widely traded in illegal online markets. These websites, also known as crypto markets, are on the dark web and cannot be accessed with regular internet browsers or search engines. Users are anonymous and transactions are made in cryptocurrencies such as Bitcoin. Law enforcement agencies are faced with the challenge of sifting through vast amounts of data to find the big players in this hidden digital environment.
Predicting success
As part of a project funded by Politie en Wetenschap, doctoral student Hanjo Boekhout, professor Frank Takes and professor Arjan Blokland developed a method to predict which users will become successful sellers. Besides the section where things are sold, the marketplace has a forum section for discussions between users and sellers. By analysing communication patterns in this forum, the researchers were able to identify key players in the network. The study was carried out using data from Evolution, one of the most popular data web marketplaces in 2014.
Two factors help predict a seller's success: Topic Engagement and Betweenness centralityTopic engagement is the frequency with which other users respond to forum topics initiated by a user. Betweenness centrality indicates how frequently a user is a link to other users in a communication network.
“Topic engagement proved to be an especially strong predictor: users who respond a lot to forum topics often turn out to be successful sellers,” Boekhout says. Betweenness centrality helped identify important players who weren't very active on the forums. “Some sellers don't post very often, but when they do, they connect different parts of the network,” Boekhout says.
Support law enforcement
The method could help law enforcement prioritize their investigations. “These marketplaces are so big that police have to be selective,” Blokland says. “Our method helps identify emerging sellers before they get really big.” The researchers hope that their work will catch the eye of law enforcement. Police scientists could continue to develop the method and try it out in investigations of other dark web markets.
Read the article “Early Warning Signals to Predict Crypto Market Vendor Success Using Darknet Forum Networks”
Text: Tom Jansen
Banner photo: Istock
