Understanding User Economic Behavior in the City Using Large-scale Geotagged and Crowdsourced Data

Abstract

The pervasiveness of mobile technologies today have facilitated the creation of massive crowdsourced and geotagged data from individual users in real time and at different locations in the city. Such ubiquitous user-generated data allow us to infer various patterns of human behavior, which help us understand the interactions between humans and cities. In this study, we focus on understanding users economic behavior in the city by examining the economic value from crowdsourced and geotaggged data. Specifically, we extract multiple traffic and human mobility features from publicly available data sources using NLP and geo-mapping techniques, and examine the effects of both static and dynamic features on economic outcome of local businesses. Our study is instantiated on a unique dataset of restaurant bookings from OpenTable for 3,187 restaurants in New York City from November 2013 to March 2014. Our results suggest that foot traffic can increase local popularity and business performance, while mobility and traffic from automobiles may hurt local businesses, especially the well-established chains and high-end restaurants. We also find that on average one more street closure nearby leads to a 4.7% decrease in the probability of a restaurant being fully booked during the dinner peak. Our study demonstrates the potential of how to best make use of the large volumes and diverse sources of crowdsourced and geotagged user-generated data to create matrices to predict local economic demand in a manner that is fast, cheap, accurate, and meaningful.