Leveraging Social Networks to Identify Likely Adopters

With the availability of social network data, it has become possible to relate the behavior of individuals to that of their acquaintances on a large scale. While the similarity of connected individuals is well established, it is unclear whether behavioral predictions based on social data are more accurate than those arising from current marketing practices. We employ a communications network of over 100 million people to forecast highly diverse behaviors, from patronizing an offline department store to responding to advertising to joining a recreational league. Across all domains, we find that social data are informative in identifying individuals who are most likely to undertake actions. In identifying such individuals, social data improved upon both demographic and behavioral models. When rich transactional data were available, social data did little to improve prediction.