Early Intervention Systems: Predicting Adverse Interactions Between Police and the Public

Abstract

Adverse interactions between police and the public hurt police legitimacy, cause harm to both officers and the public, and result in costly litigation. Early intervention systems (EISs) that flag officers considered most likely to be involved in one of these adverse events are an important tool for police supervision and for targeting interventions such as counseling or training. However, the EISs that exist are not data-driven and based on supervisor intuition. We have developed a data-driven EIS that uses a diverse set of data sources from the Charlotte-Mecklenburg Police Department and machine learning techniques to more accurately predict the officers who will have an adverse event. Our approach is able to significantly improve accuracy compared with their existing EIS: Preliminary results indicate a 20% reduction in false positives and a 75% increase in true positives.

Risk of being killed by police use of force in the United States by age, race–ethnicity, and sex

“…Both the public interest and social science are served by increasing transparency with regard to police use of force. Using such data, the research community has made strides in identifying officers most at risk of being involved in cases of excessive force (41) and system failures that result in civilian deaths (42).…”

“…We predict that between 36 and 81 American Indian/Alaska Native men and boys per 100,000 will be killed by police over the life course. Latino men and boys have an estimated risk of being killed by police of about 53 per 100,000 [41,67]. Asian/Pacific Islander men and boys face a lifetime risk of between 9 and 23 per 100,000, while white men and boys face a lifetime risk of about 39 [31,48] per 100,000.…”

The Problems With Prosecutors

“…Police departments are more strategic in the deployment of their resources and personnel; intelligence-led policing, based on sophisticated crime analysis, has become increasingly common (Ratcliffe 2016). It is also increasingly common for police departments to use data analytics to identify and to track officers who seem particularly prone to misconduct (Helsby et al 2017).…”

A Recommendation Engine to Aid in Identifying Crime Patterns

“…Continuing this tradition, a wide variety of predictive policing applications are in use by law enforcement agencies today, including algorithms that forecast geographies at high risk of imminent crime (8,9), predict recidivism to aid in sentencing (10), or identify individuals at risk for involvement in future gun violence (11). Advanced analytics have also been used in police management, such as optimizing the recruitment process for police applicants (12), tracking the locations of officers on patrol (13), and identifying officers in need of counseling or training (14).…”