Evaluating the Performance of Hierarchical Clustering algorithms to Detect Spatio-Temporal Crime Hot-Spots

Abstract

The constant growth in urbanization is a cause of significant social and economical transformations in urban areas. Areas where crime rates are above the normal level, are known as crime hot-spots. The increase in urban population is posing challenges related to the management, services and safety from criminal activities. It is important to keep an eye on criminal activities and for the law enforcement agencies, being able to provide much needed safety of public is an increasingly complex task. This complex task can be handled by new technologies which can help these agencies to effectively analyze and understand the different crime trends and patterns with respect to their geographic locations. This paper uses Hierarchical Density-based spatial clustering of applications with noise (HDBSCAN) to find spatio-temporal crime hot-spots by clustering and the results shows that this technique outperforms others.