Abstract:

The capacity to gather and scrutinise extensive crime-related data has emerged as an essential resource for law enforcement authorities.  This research analyses geographical and temporal crime trends in Illinois from 2001 to 2024, utilising geospatial analysis and time-series forecasting to pinpoint high-crime regions, seasonal variations, and socioeconomic factors. Predictive models, such as ARIMA, Kernel Density Estimation (KDE), and clustering approaches, are utilised to improve crime predictions and optimise the allocation of law enforcement resources.  The study incorporates ideas from international predictive policing projects, including the Los Angeles LASER program and Dubai’s data-driven crime reduction methods, to evaluate the practical applications of crime analytics.  This research seeks to clarify the correlation between crime patterns and socioeconomic variables such as unemployment, income, and educational attainment, with the objective of enhancing a data-driven framework for crime prevention and the optimisation of law enforcement resources.