Hidden in Plain Sight: Detecting Illicit Massage Businesses from Mobility Data

2026-02-18

AI Summary

This study addresses the challenge of identifying illicit massage businesses (IMBs) that masquerade as legitimate establishments and evade detection due to the absence of clear labels. To overcome this, the authors propose a novel approach leveraging real-world mobile location data to construct four types of visitor behavioral features that are difficult to fabricate. Within a Positive-Unlabeled (PU) learning framework, these features enable risk scoring of venues through temporal visitation pattern modeling and risk calibration, thereby supporting law enforcement in prioritizing high-risk targets for inspection. Experimental results demonstrate strong performance, with an AUC of 0.97 and an average precision of 0.84. Notably, focusing on the top 10% of venues by risk score captures 53% of known IMBs, yielding a 5.3-fold improvement in investigative efficiency.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Privacy
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Mitigating online harms, including harassment, spam, and fake reviews
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Illicit massage businesses (IMBs) masquerade as legitimate massage parlors while facilitating commercial sex and human trafficking. Law enforcement must identify these businesses within a dense population of lawful establishments, but investigative resources are limited and the illicit status of each location is unknown until inspection. Detection methods based on online reviews offer some insight, yet operators can manipulate these signals, leaving covert establishments undetected. IMBs constitute one of the largest segments of indoor sex trafficking in the United States, with an estimated 9,000 establishments. Mobility data offers an alternative to online signals, covering establishments that avoid digital visibility entirely. We derive features from mobility data spanning temporal visitation patterns, dwell times, visitor catchment areas, and demand stability. Because confirmed labels exist only for establishments identified through advertising platforms, we employ positive-unlabeled learning to address the label asymmetry in ground truth. The model achieves 0.97 AUC and 0.84 Average Precision. Four operational signatures characterize high-risk establishments: demand consistency, evening-concentrated visits, compressed service durations, and locally drawn clientele. The model produces risk scores for each business-week observation. Aggregating to the business level, prioritizing the highest-risk 10% of massage establishments captures 53% of known illicit operations, a 5.3-fold improvement over uninformed inspection. We develop a decision-support system that produces calibrated prioritization scores for law enforcement, enabling investigators to concentrate inspections on the highest-risk venues. The operational signatures may resist strategic manipulation because they reflect actual operations rather than online signals that operators can control.

Problem

• illicit massage businesses
• human trafficking
• mobility data
• positive-unlabeled learning
• law enforcement

Innovation

• mobility data
• positive-unlabeled learning
• illicit massage businesses
• operational signatures
• decision-support system