Predictive policing as a tool for crime prediction and prevention : a methodological and operational evaluation

Data-driven approaches are gaining in importance in our current digital society. In criminology, this has led to increased research interest in big data analysis and other innovative methods and applications for crime analysis such as predictive policing. Predictive policing is the use of historical crime and other data in advanced statistical models to predict where and when new crime events are likely to occur and use these predictions to proactively direct police patrols. Despite its increased use by law enforcement agencies around the world and the development of predictive policing applications by commercial software companies, academic research studying the methodological and operational dimensions of predictive policing is limited. This PhD research assesses some of the main methodological and operational considerations in the application of predictive policing and discusses the implications for policy, practice and future research