A spatial-temporal analysis of sexual-crime concentrations

• In Event: Researching sex crimes

Abstract

Big data policing has gained increasing attention in criminological research, particularly in forecasting property crimes. However, its application to sexual crime remains largely unexplored due to challenges such as underreporting and data scarcity. This descriptive study seeks to bridge this gap by analysing the spatial and temporal patterning of sexual offenses, providing a data-driven approach to examining the spatiotemporal concentration, recurrence, and environmental influences of sexual crimes. Using police-registered crime data, this research examines daily, weekly, and seasonal sexual crime cycles, incorporating a micro-geographic approach with a high-resolution meter-grid analysis to detect high-risk locations and peak time periods. Additionally, we will explore machine learning and predictive modelling techniques to assess the feasibility of predicting spatiotemporal patterns in sexual offending and identifying potential intervention points given our data and its shortcomings. The findings will provide critical insights into the role of spatial and temporal dynamics in shaping sexual crime occurrence. By evaluating the potential of big data policing in this domain, this study contributes to the broader discourse on data-driven crime prevention and public safety in urban settings, advancing knowledge on sexual crime patterns and their long-term implications. This research is part of the Big Data Policing (BIGDATPOL) program (ERC, BIGDATPOL, 101088156), which advances data-driven crime analysis.

Authors

• Fauve Duprez, Ghent University

• Robin Khalfa, Ghent University

• Wim Hardyns, Ghent University, Department of Criminology, Criminal Law and Social Law