Crime prediction through urban metrics and statistical learning
arXiv:1712.03834 · doi:10.1016/j.physa.2018.03.084
Abstract
Understanding the causes of crime is a longstanding issue in researcher's agenda. While it is a hard task to extract causality from data, several linear models have been proposed to predict crime through the existing correlations between crime and urban metrics. However, because of non-Gaussian distributions and multicollinearity in urban indicators, it is common to find controversial conclusions about the influence of some urban indicators on crime. Machine learning ensemble-based algorithms can handle well such problems. Here, we use a random forest regressor to predict crime and quantify the influence of urban indicators on homicides. Our approach can have up to 97% of accuracy on crime prediction, and the importance of urban indicators is ranked and clustered in groups of equal influence, which are robust under slightly changes in the data sample analyzed. Our results determine the rank of importance of urban indicators to predict crime, unveiling that unemployment and illiteracy are the most important variables for describing homicides in Brazilian cities. We further believe that our approach helps in producing more robust conclusions regarding the effects of urban indicators on crime, having potential applications for guiding public policies for crime control.
arXiv commentAccepted for publication in Physica A
References in corpus (18)
- Scikit-learn: Machine Learning in Python
- Statistical physics of social dynamics
- Epidemic processes in complex networks
- Solving the Quantum Many-Body Problem with Artificial Neural Networks
- Statistical physics of human cooperation
- Machine learning phases of matter
- Statistical physics of vaccination
- Learning phase transitions by confusion
- Statistical physics of crime: A review
- Interacting Individuals Leading to Zipf's Law
- Distance to the scaling law: a useful approach for unveiling relationships between crime and urban metrics
- Is this scaling nonlinear?
- Scale-adjusted metrics for predicting the evolution of urban indicators and quantifying the performance of cities
- Scaling laws in the dynamics of crime growth rate
- Rural to urban population density scaling of crime and property transactions in English and Welsh Parliamentary Constituencies
- Empirical analysis on the connection between power-law distributions and allometries for urban indicators
- Spatial correlations, clustering and percolation-like transitions in homicide crimes
- The role of city size and urban metrics on crime modeling