Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Dec;25(4):443-448.
doi: 10.1080/17457300.2018.1467461. Epub 2018 May 24.

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

Daniel A Bowen  1 , Laura M Mercer Kollar  1 , Daniel T Wu  2   3 , David A Fraser  4 , Charles E Flood  4 , Jasmine C Moore  2 , Elizabeth W Mays  2 , Steven A Sumner  1
Affiliations

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

Daniel A Bowen et al. Int J Inj Contr Saf Promot. 2018 Dec.

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.

Keywords: Violence; crime forecasting; machine learning; violent injuries.

PubMed Disclaimer

Conflict of interest statement

Disclosure statement

We declare no competing interests.

Figures

Figure 1.
Figure 1.
Number of months per year with four or more violent crime incidents in each block group, 2013–2014, DeKalb County, Georgia.
Figure 2.
Figure 2.
Occurrence of violent crime in each block group-month by year, 2013–2014, DeKalb County, Georgia. Note: Legend: light grey (0 violent crimes); medium grey (1–3 violent crimes); black (4 or more violent crimes). The 279 Census block groups are displayed along the x-axis. Each unit on the y-axis represents a one-month time period.
See this image and copyright information in PMC

References

    1. Amandus HE, Zahm D, & Friedmann R, Ruback RB, Block C, Weiss J, … Kessler D (1996). Employee injuries and convenience store robberies in selected metropolitan areas. Journal of Occupational and Environmental Medicine, 38(7), 714–720. - PubMed
    1. Berk RA, & Bleich J (2013). Statistical procedures for forecasting criminal behavior. Criminology & Public Policy, 12(3), 513–544.
    1. Bogomolov A, Lepri B, Staiano J, Oliver N, Pianesi F, & Pentland A (2014). Once upon a crime: Towards crime prediction from demographics and mobile data. In Proceedings of the 16th international conference on multimodal interaction (pp. 427–434). Istanbul, Turkey: ACM.
    1. Butts JA, Roman CG, Bostwick L, & Porter JR (2015). Cure violence: A public health model to reduce gun violence. Annual Review of Public Health, 36, 39–53. - PubMed
    1. Chen C, Liaw A, & Breiman L (2004). Using random forest to learn imbalanced data (pp. 1–12). Berkeley: University of California.

LinkOut - more resources