PREDICTIVE POLICING

Abstract

Crime control strategies in the past have largely been focused on reactive tactics, while the focus of policing was to respond quickly to incidents and crimes. However, as the crime and security situation changed, so did the paradigm shift from a reactive style of policing to proactive policing. Proactive work aims to prevent crime rather than just react to it. It has been shown that crime prevention is more closely related to proactive policing than to reactive policing. Crime prevention strategies such as community-oriented policing, problem-oriented policing, intelligence-led policing were introduced with having in mind proactive policing. In recent decades, a new proactive data-driven policing strategy has emerged, namely predictive policing. It uses information technology, data and analytical techniques in order to identify the most likely places and times of future criminal events or persons at high risk of committing or becoming victims of a crime. The use of predictive analytics and machine learning has attracted enormous attention, linking predictive policing with digital innovation. Although it can be argued that data collection and processing has always been an important aspect of policing, technological advances and the increased availability of police data have led to a shift from predominantly reactive policing to proactive policing. It should be emphasized that predictive policing is not intended to replace the already tried and tested proactive policing techniques such as evidence-based policing. Improvements to traditional proactive policing techniques such as machine learning and sophisticated algorithms are enabling the police to track both individuals and areas with greater accuracy in order to predict when, where and by whom a crime may be committed.