Improving Pre-Launch Diffusion Forecasts: Using Synthetic Networks as Simulated Priors

Journal of Marketing Research (2013)

Robert H. Smith School Research Paper

78 Pages Posted: 20 Nov 2013

See all articles by Michael Trusov

Michael Trusov

University of Maryland - Robert H. Smith School of Business

William Rand

North Carolina State University

Yogesh V. Joshi

University of Maryland - Department of Marketing

Date Written: August 13, 2013

Abstract

While the role of social networks and consumer interactions in new product diffusion is widely acknowledged, such networks and interactions are often unobservable to the firm/researcher. What may be observable, instead, are aggregate diffusion patterns for past products adopted within a particular social network. We propose an approach for identifying systematic conditions that are stable across diffusions, and hence are "transferrable" to new product introductions within a given network. Using Facebook apps data, we show that incorporation of such systematic conditions improves pre-launch forecasts. Our research bridges the gap between the disciplines of Bayesian statistics and agent-based modeling by demonstrating how stochastic relationships simulated within complex systems can be used as meaningful inputs for Bayesian inference models.

Keywords: agent-based models, complex systems, Bayesian inference, consumer networks, diffusion, pre-launch foecasts

Suggested Citation

Trusov, Michael and Rand, William and Joshi, Yogesh V., Improving Pre-Launch Diffusion Forecasts: Using Synthetic Networks as Simulated Priors (August 13, 2013). Journal of Marketing Research (2013); Robert H. Smith School Research Paper. Available at SSRN: https://ssrn.com/abstract=2353688

Michael Trusov

University of Maryland - Robert H. Smith School of Business ( email )

College Park, MD 20742
United States
(301) 405-5878 (Phone)
(301) 405-0146 (Fax)

HOME PAGE: http://www.emodeler.us

William Rand (Contact Author)

North Carolina State University ( email )

Raleigh, NC 27695
United States

Yogesh V. Joshi

University of Maryland - Department of Marketing ( email )

College Park, MD 20742
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
193
Abstract Views
783
rank
154,958
PlumX Metrics