Applying Check-in Data and User Profiles to Identify Optimal Store Locations in a Road Network

Spatial information analysis has gained increasing attention in recent years due to its wide range of applications, from disaster prevention and human behavioral patterns to commercial value. This study proposes a novel application to help businesses identify optimal locations for new stores. Optimal store locations are close to other stores with similar customer groups. However, they are also a suitable distance from stores that might represent competition. The style of a new store also exerts a significant effect. In this paper, we utilized check-in data and user profiles from location-based social networks to calculate the degree of influence of each store in a road network on the query user to identify optimal new store locations. As calculating the degree of influence of every store in a road network is time-consuming, we added two accelerating algorithms to the proposed baseline. The experiment results verified the validity of the proposed approach.