The present chapter aims to exhibit the core risk indicators of crime against women in West Bengal, embellish the spatial association of the potential factors and occurrence mechanisms, and predict future crime hotspots using geospatial modeling by incorporating spatially contextual factors within a Geographic Information System (GIS) environment. Factor analysis has been executed to unveil significant determinants of criminality against women in Bengal, and geographically weighted regression (GWR), a spatial econometric statistic, is applied to make individual coefficient estimations of determinants over space and predict future vulnerable areas by considering the spatial variation in the relationship among the determinants. The spatial weights used in GWR, which measure spatial associations, have strong policy implications, with the potential for far more targeted space-specific interventions in the regional context.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Predicting Future Crime Hotspots Using Statistical Techniques and GIS

  • Priyanka Biswas,
  • Nilanjana Das Chatterjee

摘要

The present chapter aims to exhibit the core risk indicators of crime against women in West Bengal, embellish the spatial association of the potential factors and occurrence mechanisms, and predict future crime hotspots using geospatial modeling by incorporating spatially contextual factors within a Geographic Information System (GIS) environment. Factor analysis has been executed to unveil significant determinants of criminality against women in Bengal, and geographically weighted regression (GWR), a spatial econometric statistic, is applied to make individual coefficient estimations of determinants over space and predict future vulnerable areas by considering the spatial variation in the relationship among the determinants. The spatial weights used in GWR, which measure spatial associations, have strong policy implications, with the potential for far more targeted space-specific interventions in the regional context.