Ability of crime, demographic and business data to forecast areas of increased violence

Abstract

Identifying geographic areas and time periods of increased violence is of considerable importance in prevention planning. This study compared the performance of multiple data sources to prospectively forecast areas of increased interpersonal violence. We used 2011-2014 data from a large metropolitan county on interpersonal violence (homicide, assault, rape and robbery) and forecasted violence at the level of census block-groups and over a one-month moving time window. Inputs to a Random Forest model included historical crime records from the police department, demographic data from the US Census Bureau, and administrative data on licensed businesses. Among 279 block groups, a model utilizing all data sources was found to prospectively improve the identification of the top 5% most violent block-group months (positive predictive value = 52.1%; negative predictive value = 97.5%; sensitivity = 43.4%; specificity = 98.2%). Predictive modelling with simple inputs can help communities more efficiently focus violence prevention resources geographically.

Building capacity for injury prevention: a process evaluation of a replication of the Cardiff Violence Prevention Programme in the Southeastern USA

“…Public health agencies have the authority to receive protected health information and are the ideal partners for receiving, processing and aggregating data from multiple sources. Summary information in the form of aggregate maps and lists of businesses experiencing high counts of violence can then be shared with the community safety partnership for injury prevention and control activities 5 23 24. The Cardiff Model collects, aggregates and shares violence-related injury data, potentially through a public health agency, in a form that may be used by LE and other partners.…”

The Death of Freddie Gray and Its Impact on Homicides in Baltimore and Maryland

“…Studies have shown spatial clustering of homicides to be associated with higher rates of segregation, poverty, and economic disparity (17,18). Another study found that historic crime data and demographic data reflecting poverty were best able to predict future violent crime (19).…”

“…A similar approach emphasizing collaboration with the DEA allowed for early recognition of the recent fentanyl epidemic in Maryland and timely implementation of public health interventions (22). Although several studies have evaluated crime outcomes using mapping techniques (18,19,21,23,24), the current study highlights how the effects of a unique societal sentinel event such as the death of Freddie Gray are particularly well suited to in‐depth analysis by GIS.…”

Implementation and initial analysis of Cardiff Model data collection procedures in a level I trauma adult emergency department

“…1 Current law enforcement decision-making and resource allocation use predictive geographical models created exclusively from law enforcement data. 2 Advancements in model predictive accuracy have enabled more robust discussions around community violence than were possible with hotspot mapping alone. However, significant limitations of solely relying on law enforcement data remain since datasets are incomplete and do not accurately represent community violence due to underreporting of violent crimes.…”

“… 25 Hospital acquired data may also assess effectiveness of interventions and allow for direct targeting of community areas with high violence rates. 2 18 ED data collection, therefore, is valuable and versatile for current violence prevention initiatives.…”