Criminal Activity Monitoring System: Targeting Africans and East Asian Communities in Dubai

This dissertation investigates crime patterns among African and East Asian communities in Dubai, focusing on geographic hotspots, temporal trends, victim demographics, and the use of machine learning for predictive crime modeling. The research addresses the challenges faced by these communities, including labor exploitation, financial fraud, and human trafficking, within the socio-economic context of a rapidly growing urban city. Building on existing studies of urban crime, this research aimed to explore the spatial, temporal, and demographic dynamics of crimes and assess the potential of predictive models to assist law enforcement in crime prevention and resource allocation. A mixed-methods approach was employed, incorporating descriptive and machine learning analysis. Data were collected from open-source crime datasets and enriched with socio-economic variables and temporal details. Techniques such as clustering, classification using Random Forest and Logistic Regression, and anomaly detection were applied to uncover insights. Geographic hotspots were identified, temporal crime trends analyzed, and predictive models were evaluated for their effectiveness in classifying crime outcomes. The findings revealed significant spatial and temporal patterns. Bur Dubai, Jebel Ali, and International City emerged as hotspots, with labor exploitation concentrated in industrial zones and financial fraud and trafficking dominating urban hubs. Temporal analysis showed crime peaks in March, October, and December, suggesting seasonal influences. Demographically, socio-economic vulnerabilities were strongly linked to crime severity, with low-income groups disproportionately affected by labor exploitation and financial fraud. Machine learning models demonstrated potential, with the Random Forest Classifier achieving 78.33% accuracy, but limitations were evident, particularly in handling imbalanced datasets and predicting high-severity or unsolved cases. The research contributes to the literature by highlighting the intersection of geography, demographics, and crime dynamics in Dubai’s expatriate communities. It underscores the need for targeted interventions, such as labor law enforcement in industrial zones and fraud prevention programs in urban hubs. Key recommendations include enhancing data collection systems to include real-time and granular socio-economic data, adopting advanced machine learning techniques to address class imbalance, and promoting community policing to strengthen trust and collaboration. The study’s limitations, such as reliance on secondary data and the narrow focus on two communities, set the parameters for future research. Expanding the scope to include other expatriate groups and integrating live data streams would enhance the understanding of Dubai’s crime dynamics. Furthermore, exploring the socio-economic impact of policy interventions over time could provide valuable insights for policymakers and law enforcement agencies. This research highlights the importance of data-driven approaches in urban crime analysis and policymaking, offering actionable insights for fostering safer and more inclusive communities.