Studying spatial interactions between commercial activities in the city from online location-based social networks

In this work we study spatial interactions between different business activities in the city from the fine-grained mobility traces collected by online-location based social networks. We study co-location patterns of various venues in an urban environment and propose a methodology to assess flows of users between them. The result of the analysis we explore to tackle the optimal business placement problem for the three different retail chains in New York. We formalize this problem as a machine-learning task where we aim to predict potential popularity of a store if placed in a given area. We devise a number of signals to describe the area including place-geographic features, e.g, density, heterogeneity of places, and mobility-based features, e.g., flows of users towards and inside the area. Among others, we show that the presence of place-attractors (e.g., airport, train station) and competing venues in the area are strong indicators of the popularity across all considered chains. However, the best performance is achieved when we consider the fusion of mobility and place-geographic features.