Studying Spatial and Temporal Visitation Patterns of Points of Interest Using SafeGraph Data in Florida

SafeGraph is a commercial provider of massive Point of Interest (POI) data, including visitation patterns in North America. Although the data source does not share specific travel trajectories, the data available includes daily and monthly POI visitation numbers for over 160 categories, as well as information about where visitors come from and which other POI categories they visit. This allows analysts to gain insight into travel behavior in a geographic region over time. This study analyzes various aspects of visitation patterns that can be derived from the SafeGraph dataset for Florida. Using three major Florida cities, namely Miami, Orlando and Jacksonville, temporal patterns of daily and monthly visit numbers are correlated between various POI categories, and the effect of a short event (Hurricane Irma) on daily visitation numbers around the event is explored. In addition, travel distances from home to POIs are compared between different POI categories, and Ordinary Least Squares (OLS) regression models are used to identify factors associated with increased or decreased distance between home and a specific POI category. The study concludes that the aggregated data provided on the SafeGraph platform helps the GIScience community to learn more about travel patterns in both the spatial and the temporal domains