Nudging Mobile Customers with Real-Time Social Dynamics

Abstract

The proliferation of mobile and sensor technologies has contributed to the rise of location-based mobile targeting. Beyond the location, time and spatial context of individuals, the social context wherein they are embedded can reveal rich information about individual behavior. In this study, we automatically detected the real-time social contexts of customers based on their detailed GPS trajectories using machine-learning methods. To evaluate the effectiveness of mobile targeting under different social contexts, we designed a randomized field experiment in a large shopping mall in 2015. Our analyses indicated significant heterogeneity in consumer behavior under different social contexts. We found a customer in a group with others is on average 1.5 times more responsive to mobile promotions than is a solo shopper, and this impact increases with increased group size (from dyad to triad). We also found significant heterogeneous interactions between mobile promotion design and social contexts. Overall, our study demonstrates the potential of inferring individuals’ social contexts from their movement trajectories and the value of leveraging such real-time social dynamics for improved mobile-targeting effectiveness.