Spatial Co-location Pattern Mining—A Survey of Recent Trends

Spatial co-location pattern mining conception was introduced to examine the existence of objects often found together as patterns of interest. Detecting patterns from spatial data is a task of importance as co-location pattern mining has various applications such as in criminology, ecology, epidemiology, recommendation systems, understanding urban functions and so on. However, due to the absence of notion of transactions and the complexity in spatial data have led to discovery of useful spatial patterns with techniques other than association rules. For spatial co-location pattern mining study, which is not well explored, we provide in this paper a general framework, highlight distinct types of co-location patterns, and present an overview of the state-of-the-art methods in the field of co-location pattern mining. Finally, we conclude our survey by discussing the unresolved challenges in this field.