Analyzing Purchase Decisions Using Dynamic Location Data

Retailers’ efforts to monetize consumer location data remain dominated by inefficient protocols (e.g., geofencing) that customize marketing interactions based solely on app users’ current location. Although extant trajectory mining techniques can remedy these shortcomings, they require high-frequency data, which poses severe risks consumers’ privacy. The authors present a novel method extract value from low-granularity urban mobility and demonstrate its use in analyzing gas station choice customers. also used infer visits, contain 1.06 million records nearly 27,000 devices observed near selected retailers including stations during six-month period Staten Island, New York. pool trajectories several days dynamically calculate the distance of stores anticipated trajectories. They then supplement with station-level daily fuel prices estimate conditional logit model assess how consumers trade off versus store distance. In addition generally high loyalty, find strongly prefer not deviate far their common for fueling trips. Applying methods predictive context, newly acquired customers studied be between $3.00 $7.59.