Evaluating the Impact of Public Safety Measures on Crime Reduction: A Historical Data Perspective

The purpose of this study is to assess the impact of various public safety measures adopted in Chennai between 2010 and 2023 on crime reduction utilizing a historical data-driven approach. Public safety measures, including as upgraded surveillance systems, street lighting, and community policing efforts, have been implemented to address rising crime rates in critical regions of the city. By evaluating crime statistics from the previous decade, this research tries to establish the effectiveness of these strategies in lowering criminal activity throughout various zones of Chennai. Advanced machine learning methods, such as Random Forest and Gradient Boosting, are used to model and forecast crime trends before to and following the deployment of safety measures. A Difference-in-Differences (DiD) approach is also used to evaluate crime rates in regions where public safety measures have been implemented to control areas that have not received such interventions. Spatial clustering algorithms like K-means and DBSCAN are frequently used to detect crime hotspots and monitor their evolution over time. The findings show that areas with enhanced illumination and community-based policing had a large fall in property crimes and petty theft, while zones with surveillance cameras showed a big decrease in violent crimes. The data imply a 20-30% overall reduction in crime in locations where numerous public safety measures were implemented concurrently. This study emphasizes the significance of a diversified approach to crime prevention, as well as a data-driven strategy to optimize public safety measures. The study provides policymakers with concrete knowledge to improve crime prevention techniques in urban environments such as Chennai.