Prostitution Arrest Spatial Forecasting in an Era of Increasing Decriminalization

Abstract

There is ongoing debate regarding the merits of decriminalization or outright legalization of commercial sex work in the United States. A few municipalities have officially legalized both the selling and purchasing of sex, while others unofficially criminalize purchasing sex but have decriminalized its sale. In addition, there are many other locales with no official guidance on the subject but have unofficially decriminalized sex work by designating specific areas in an urban landscape safe from law enforcement for commercial sex, by quietly ceasing to arrest sex sellers, or by declining to prosecute anyone selling or attempting to sell sex. Despite these efforts, it remains crucial to understand where in an urban area commercial sex exchanges occur—legalization and decriminalization may result in fewer arrests but is likely to increase the overall size of the sex market. This growth could result in an increase in sex trafficking victimization, which makes up the majority of commercial sex sellers in any domestic market. Given the distribution of prostitution activities in most communities, it is possible to use high-fidelity predictive models to identify intervention opportunities related to sex trafficking victimization. In this research, we construct several machine learning models and inform them with a range of known criminogenic factors to predict locations hosting high levels of prostitution. We demonstrate these methods in the city of Chicago, Illinois. The results of this exploratory analysis identified a range of explanatory factors driving prostitution activity throughout Chicago, and the best-performing model correctly predicted prostitution frequency with 94% accuracy. We conclude by exploring specific areas of under- and over-prediction throughout Chicago and discuss the implications of these results for allocating social support efforts.