GIS and Anti-Crime Measures

| |

Spatio-temporal crime pattern analysis has become an important policing tool for crime prevention. In fact, crime mapping and pattern observations have been utilized for many decades. Recent approaches generally fall in the categories of stochastic, rule-based models, and more abstract models that utilize minimal input but look at simple benefits and deterrence to criminals that informs where crime is likely to occur.[1] Knowing when and where a crime is likely to occur helps police plan where to allocate their resources at different times of the day.

Stochastic approaches utilize data collection for given areas, then a probability map can be built using Bayesian modeling methods, including using Markov chain Monte Carlo simulation methods, that look at probability of occurrence of an event in a given place and time.[2] These methods tend to minimize specific factors but look more at the location, the presence of crime fighting resources, and probability of crime as a way to determine likelihood of crime. While generally simple, such stochastic models simplify data collection efforts and can help police determine crime locality without always understanding what factors might be affecting crime in a given area.

Other methods utilize spatio-temporal modeling that look at the presence of individuals likely to do a crime, areas they are willing to travel to, including their benefits for criminals, the effect of crime deterrence, and then look at these factors as push and pull factors, or utilizing more abstract modeling methods, to see which regions of a given city are likely to attract more crime due to low deterrence, high presence of crime factors, and potential benefits for crime in a given area. This type of modeling looks at the utility of actions to individuals willing to commit a crime, going beyond probability-based approaches but looking at benefits and deterrence factors. In effect, the resources available to combat crime are assessed relative to the areas’ benefits to criminals and their presence using a retail modeling approach.[3] This type of modeling was, in fact, very accurate in demonstrating the pattern of rioting during the London 2011 riots, showing its potential future use for policing efforts.  Overall, these methods demonstrate a wide and growing field of crime prevention utilizing spatial and GIS approaches.

From Davies et al., 2016: "the results show good qualitative agreement, with 26 of the 33 boroughs showing rioter percentages in the same or adjacent bands as the data. The remaining discrepancy may be accounted for by factors specific to the London disorder, such as communication between groups, other activity patterns occurring at the time, or social factors beyond the scope of this work. "
From Davies et al., 2016: “the results show good qualitative agreement, with 26 of the 33 boroughs showing rioter percentages in the same or adjacent bands as the data. The remaining discrepancy may be accounted for by factors specific to the London disorder, such as communication between groups, other activity patterns occurring at the time, or social factors beyond the scope of this work.”

References

[1] For examples of these types of approaches, see:  Liu, L., & Eck, J. (Eds.). (2008). Artificial crime analysis systems: using computer simulations and geographic information systems. Hershey: Information Science Reference.

[2] For more on anti-crime measures using probability or Bayesian modeling, see:  Law, J., Quick, M., & Chan, P. (2014). Bayesian Spatio-Temporal Modeling for Analysing Local Patterns of Crime Over Time at the Small-Area Level. Journal of Quantitative Criminology, 30(1), 57–78.

[3] For more on this model, see:  Davies, T. P., Fry, H. M., Wilson, A. G., & Bishop, S. R. (2013). A mathematical model of the London riots and their policing. Scientific Reports, 3:1303.

Related Articles

Share this article


Enter your email to receive the weekly GIS Lounge newsletter: