The effect of differential victim crime reporting on predictive policing systems

TL;DR

This paper investigates how variations in victim crime reporting rates across areas can bias predictive policing models, potentially causing misallocation of police resources and affecting fairness.

Contribution

It demonstrates the impact of differential victim reporting on predictive policing outcomes using a simulation based on Bogotá data, highlighting potential fairness issues.

Findings

Differential reporting rates can shift predicted crime hotspots.

Biases may cause over-policing in high-reporting areas.

Under-policing may occur in high-crime, low-reporting areas.

Abstract

Police departments around the world have been experimenting with forms of place-based data-driven proactive policing for over two decades. Modern incarnations of such systems are commonly known as hot spot predictive policing. These systems predict where future crime is likely to concentrate such that police can allocate patrols to these areas and deter crime before it occurs. Previous research on fairness in predictive policing has concentrated on the feedback loops which occur when models are trained on discovered crime data, but has limited implications for models trained on victim crime reporting data. We demonstrate how differential victim crime reporting rates across geographical areas can lead to outcome disparities in common crime hot spot prediction models. Our analysis is based on a simulation patterned after district-level victimization and crime reporting survey data for Bogot\'a, Colombia. Our results suggest that differential crime reporting rates can lead to a displacement of predicted hotspots from high crime but low reporting areas to high or medium crime and high reporting areas. This may lead to misallocations both in the form of over-policing and under-policing.