New Crime Prediction Insights

Understanding the factors shaping urban crime is crucial for building safe and sustainable cities. This work, supported by the US-Japan Foundation, uses Machine Learning to carefully examine existing urban datasets from New York and to unravel how urban structure and mobility combine with social-environmental factors to shed light on why and when reported crimes change across different settings. We identify temperature and mobility as the most consistent and dominant predictors at both the citywide and borough levels. Socio-economic and demographic variables indicate more spatially heterogeneous impacts. We propose three actionable pathways for sustainable urban systems: 1) Climate-responsive infrastructure, 2) Mobility-centered safety planning, 3) Community-driven environmental governance. For more...