Simultaneous detection of multiple areas-of-interest using geospatial data from an online food delivery platform (industrial paper)

Abstract

With the development of mobile Internet, online food delivery (OFD) services have become increasingly popular in our daily lives. OFD platforms rely heavily on accurate Areas-of-Interest (AOIs) information on many aspects of their operations to pinpoint customers' exact locations and to define the service areas of restaurants. Recently, OFD platforms have started to tap into the vast amount of geospatial data generated in their day-to-day business to improve the accuracy of their AOI information. Although there has been a proliferation of studies that leverage such data to detect the underlying AOIs, for example, to identify the names and spatial boundaries of the AOIs, they focus on the single-AOI detection problem, that is, they detect AOIs one at a time and ignore their spatial dependency. This would end up with inconsistent results, i.e., AOIs with overlapping spatial boundaries. To address this issue, we propose a new approach to detect multiple AOIs simultaneously and solve the multi-AOIs detection problem. In our approach, we first apply the existing single-AOI detection algorithms to generate candidate spatial boundaries for AOIs in a neighborhood, and then develop a Binary Integer Linear Programming (BILP) model to determine the best candidate spatial boundaries for these AOIs while accounting for their spatial dependency. We conduct numerical experiments using real data from Meituan, the largest OFD platform in China. Results show that our model not only produces consistent AOI boundaries, but also improves the average F1 score by 4.7%.