Quantifying the Relationship between Large Public Events and Escort Advertising Behavior

ABSTRACT

We study online escort advertisement responses to large scale public events using a time series anomaly detection framework. We analyze advertisement volume, approximations of advertiser volumes, and further devise a measure for movement derived from the spatio-temporal behavior amongst related advertisements. Our results imply that a variety of events correlate with unusual increases in sex worker activity, including an influx of providers that are new to the respective event location. The findings indicate that there are strong market responses to some public events and that Super Bowl events which received heightened attention by authorities and news media due to a perceived link to human trafficking for sexual exploitation do not stand out amongst these events in the effect on the market that we measured.

KEYWORDS:

• Anomaly detection
• super bowl
• events
• escort advertisements

Additional information

Funding

This work was supported by the Defense Advanced Research Projects Agency [FA8750-14- 2-0244];National Institute of Justice [2013-IJ-CX-K007];National Science Foundation (US) [1320347].