Predicting Individual Behavior with Social Networks

Posted: 28 Feb 2014

See all articles by Sharad Goel

Sharad Goel

Stanford University

Daniel G. Goldstein

Microsoft Research New York City; London Business School

Date Written: 2014

Abstract

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. Although 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 off-line 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 various actions, and moreover, such data improve on both demographic and behavioral models. There are, however, limits to the utility of social data. In particular, when rich transactional data were available, social data did little to improve prediction.

Keywords: social networks, targeting, electronic commerce, homophily, product, computational social science

Suggested Citation

Goel, Sharad and Goldstein, Daniel G., Predicting Individual Behavior with Social Networks (2014). Marketing Science, Vol. 33, No. 1, 2014; pp. 82-93; DOI: 10.1287/mksc.2013.0817. Available at SSRN: https://ssrn.com/abstract=2397052

Sharad Goel (Contact Author)

Stanford University ( email )

475 Via Ortega
Stanford, CA 94305
United States

HOME PAGE: http://5harad.com

Daniel G. Goldstein

Microsoft Research New York City ( email )

641 Avenue of Americas
New York, NY 10011
United States

London Business School ( email )

Sussex Place
Regent's Park
London, London NW1 4SA
United Kingdom
+44 0 20 7000 8611 (Phone)
+44 0 20 7000 8601 (Fax)

HOME PAGE: http://www.dangoldstein.com

Register to save articles to
your library

Register

Paper statistics

Abstract Views
807
PlumX Metrics