A Comparative Simulation Study of the Fairness and Accuracy of Predictive Policing Systems in Baltimore City
This work addresses fairness concerns in predictive policing for city policymakers by providing a comparative simulation methodology, though it is incremental in building on prior studies of bias.
The study compared the fairness and accuracy of predictive policing versus hot spots policing in Baltimore, finding that predictive policing was more fair and accurate in the short term but amplified bias faster over time, with bias sometimes favoring over-policing in White neighborhoods.
There are ongoing discussions about predictive policing systems, such as those deployed in Los Angeles, California and Baltimore, Maryland, being unfair, for example, by exhibiting racial bias. Studies found that unfairness may be due to feedback loops and being trained on historically biased recorded data. However, comparative studies on predictive policing systems are few and are not sufficiently comprehensive. In this work, we perform a comprehensive comparative simulation study on the fairness and accuracy of predictive policing technologies in Baltimore. Our results suggest that the situation around bias in predictive policing is more complex than was previously assumed. While predictive policing exhibited bias due to feedback loops as was previously reported, we found that the traditional alternative, hot spots policing, had similar issues. Predictive policing was found to be more fair and accurate than hot spots policing in the short term, although it amplified bias faster, suggesting the potential for worse long-run behavior. In Baltimore, in some cases the bias in these systems tended toward over-policing in White neighborhoods, unlike in previous studies. Overall, this work demonstrates a methodology for city-specific evaluation and behavioral-tendency comparison of predictive policing systems, showing how such simulations can reveal inequities and long-term tendencies.