Researchers at North Carolina State University have collaborated with an anti-human trafficking organization, Global Emancipation Network, to develop computer models that can help combat human trafficking. The models rely on publicly available data to identify massage businesses most likely to violate sex trafficking and labor trafficking laws.
“It is well established that massage businesses can be used as fronts for illegal operations involving sex trafficking and labor trafficking,” says Margaret Tobey, PhD. student at NC State and corresponding author of an article on the job. “However, most massage businesses are legitimate. And it’s difficult for law enforcement or other organizations to determine which businesses are legitimate and which are fronts for illegal activity.”
“Our goal was to create statistical tools that could help competent authorities determine which companies present risk factors related to trafficking, so that they can determine on which sites to focus their investigative efforts,” explains Maria Mayorga, co-author of the paper and professor in the Edward P. Fitts Department of Industrial and Systems Engineering at NC State.
“We also wanted to make sure that the tools we developed were user-friendly enough to be practical for both law enforcement and organizations that focus on helping victims of sex and labor trafficking. hard work,” Tobey said.
To develop the tools, the researchers first interviewed law enforcement, government officials and experts from organizations that work with survivors of sex and labor trafficking. The interviews aimed to identify variables associated with an increased likelihood that a massage business might be engaged in illegal activities. For example, businesses that catered almost exclusively to male customers were more likely to be associated with sex trafficking.
Once the researchers identified a series of relevant variables, they searched for publicly available data sources related to those variables. For example, online customer review sites allowed researchers to estimate the proportion of men among a company’s customers. Other data sources included census data for the neighborhood a business was located in, geographic proximity to various other businesses and transportation hubs, and more.
Ultimately, the researchers developed two computer models that provide users with probability scores on how likely a given massage company is to engage in illegal activity.
“We trained and validated these models using data from Florida and Texas because we were able to collect strong datasets from those states,” Tobey says. “We found that each model had strengths that could appeal to different users depending on their goals.”
One model, called the risk score model, had fewer false positives, meaning that if the model indicated a company was likely to engage in illegal activity, it was more likely to be correct. But this model was also more likely to list some illicit companies as legitimate.
In contrast, the second model, called the decision tree model, had fewer false negatives. In other words, if the decision tree model indicated that a company was unlikely to engage in illegal activities, it was more likely to be correct. But it was also more likely to list legitimate companies as suspicious.
“It’s a compromise,” Tobey says. “If you have very limited resources, you’ll probably want to use the risk score model because you’re more likely to find companies that engage in illegal activity. However, you might also miss some. If you have enough resources, you’ll probably want to use the decision tree model because you’re less likely to miss an illegal operation.
“Ultimately, both of these models can be used by affected parties to prioritize which companies merit investigation.”
Researchers are currently developing a user-friendly decision support tool that can be deployed to law enforcement and non-profit organizations to facilitate investigations into sex and human trafficking.
“We believe this tool can empower victims of trafficking, improve public safety and contribute to the development of evidence-based public policies that address these issues,” says Sherrie Caltagirone, co-author of the article. and Executive Director of the Global Emancipation Network. .
The article, “Interpretable models for automated detection of human trafficking in illicit massage businesses,” is published in the journal IISE Transactions. The article was co-authored by Ruoting Li, a Ph.D. student at NC State; and Osman Özaltın, associate professor in the Edward P. Fitts Department of Industrial and Systems Engineering at NC State.
Margaret Tobey et al, Interpretable Models for Automated Detection of Human Trafficking in Illicit Massage Businesses, IISE Transactions (2022). DOI: 10.1080/24725854.2022.2113187
Quote: New IT tools to target sex and labor trafficking operations (October 12, 2022) Retrieved October 12, 2022 from https://phys.org/news/2022-10-tools-sex-labor- trafficking.html
This document is subject to copyright. Except for fair use for purposes of private study or research, no part may be reproduced without written permission. The content is provided for information only.