Visual Analysis of Predictive Policing to Improve Crime Investigation

In recent years, crime analysts have pointed to the potential benefits of focusing crime prevention efforts using visual analysis. From previous studies and analysis, crime is not spread evenly across city landscapes, there is significant clustering of crime in small places, or “hotspots”, that generate half of all criminal events. Hotspots policing has become a very popular way for police departments to prevent crime, however, visual analysis of predicting policing will aid in improving crime investigation. In our analysis, we want to identify if crime is spread uniformly according to population density or whether certain socio-economic attributes account for an increase or decrease in crime. So, the aim of the study is to gather intelligence on crime for use by police forces, neighbourhood watch patrols and concerned residents. The intelligence will cover crime hotspots, temporal analysis of crime and uncover relationships which can be used to formalise a basic predictive model. Using this information, stakeholders can adjust the implementation of resources to specific geographic locations, at particular times, or to areas associated with a strong demographic indicator. For this research work, we considered London crime dataset.