2021 - Working Papers: Marketing

Retailers’ efforts to monetize consumer location data remain dominated by inefficient protocols (e.g., geo-fencing) that customize marketing interactions based solely on app users’ current location. While trajectory mining approaches in the literature remedy these shortcomings, they have hitherto been limited to high-frequency location data, precluding their use outside shopping malls. We present a novel method to use low-granularity urban mobility data in consumer choice models, and analyze gas station choice during a six-month period in Staten Island, NY. Our data, also used to infer gas station visits, contain 11.7 million location records on 273 thousand devices observed near selected retailers including gas stations. We pool consumers’ mobility trajectories from several days to dynamically derive the distance of stores from consumers’ “anticipated trajectories.” We then supplement our data with station-level daily fuel prices and estimate a conditional logit model to assess how consumers trade off gas prices versus store distance. Further to a generally high station loyalty, we find that consumers strongly prefer not to deviate far off their common trajectories for fueling trips. We demonstrate the importance of this result through a counterfactual simulation, which reveals how the busiest traffic flows affect the geographic structure of competition in gasoline retail.