A Novel Analytical Framework for Modeling Crime Spatial Patterns Using Composite Urban Environmental Factors

The urban physical environment is composed of multiple elements that collectively influence the spatial pattern of crime. Existing research has predominantly focused on the relationship between individual types of facilities and crime, yet there remains a gap in comprehensively examining the integrated effects of the urban physical environment. This study, taking 87 police precincts in the central city of Changchun as units of analysis, innovatively constructs an integrated “Factor Analysis–Negative Binomial Regression” framework. First, factor analysis is applied to reduce the dimensionality of 14 categories of Points of Interest (POI) data, extracting three comprehensive factors that characterize the macro-level functional structure of the city: the “Business and Economic Activities Factor,” the “Residential, Educational, and Transportation Factor,” and the “Leisure and Entertainment Factor.” This approach effectively addresses the issue of multicollinearity among variables and uncovers the underlying macro-level functional factors. Subsequently, a negative binomial regression model is employed to analyze the impact of each factor on crime counts. The results indicate that: (1) The spatial distribution of urban crime is markedly heterogeneous and is systematically driven by the urban functional structure; (2) Both the “Business and Economic Activities Factor” and the “Leisure and Entertainment Factor” exhibit significant positive effects on crime, with each unit increase in their scores associated with an approximately 20% increase in the relative risk of crime; (3) The influence of the “Residential, Educational, and Transportation Factor” is not significant. Collectively, the findings demonstrate that shifting the perspective from “micro-level facilities” to “macro-level functional dimensions” can provide deeper insights into the fundamental formative mechanisms underlying the spatial pattern of crime.