Understanding Public Safety Trends in Calgary through data mining

TL;DR

This work addresses how urban safety in Calgary can be understood through multi-source open data and data mining. It combines geospatial visualization, correlation analysis, and predictive modeling with clustering to identify determinants of crime, disorder, and traffic incidents. Key contributions include integrating streetlights, trees, and pet registrations with safety data, and applying advanced clustering methods (CLARANS, CLIQUE) alongside regression analyses, to generate actionable insights for urban governance. The findings highlight strong links between housing structures and safety outcomes, demonstrate the potential and limits of clustering on such data, and provide a data-driven foundation for targeted policy interventions in a growing smart-city context.

Abstract

This paper utilizes statistical data from various open datasets in Calgary to to uncover patterns and insights for community crimes, disorders, and traffic incidents. Community attributes like demographics, housing, and pet registration were collected and analyzed through geospatial visualization and correlation analysis. Strongly correlated features were identified using the chi-square test, and predictive models were built using association rule mining and machine learning algorithms. The findings suggest that crime rates are closely linked to factors such as population density, while pet registration has a smaller impact. This study offers valuable insights for city managers to enhance community safety strategies.

Figures (33)

• Figure 1: Generalized pseudocode of traditional K-means
• Figure 2: Generalized version of CLARANS algorithm
• Figure 3: Generalized version of DBSCAN algorithm
• Figure 4: Generalized version of OPTICS algorithm
• Figure 5: Generalized version of Agglomerative Hierarchical Clustering algorithm