AN APPLIED PREDICTIVE MODELING OF BRAND EQUITY INDUCING SOCIAL MEDIA BRAND-RELATED ENGAGEMENT

Abstract

This study presents a machine learning approach using conditional inference tree (Ctree) to determine how brand equity can be used to factually engage consumers into social media brand-related activities. Using the Ctree algorithm (Hothorn, Hornik, & Zeileis, 2006), a predictive model was computed using self-reported data on consumers’ perceptions of brand equity (Aaker, 1991) and engagement into social media brand-related behavior (Muntinga, Moorman, & Smit, 2011) from a sample of 690 individuals. The predictive modeling analysis revealed 5 different rules (patterns) that trigger social media brand-related behavior. Each rule comprises behavioral engagement discriminating low, medium, and high levels of consumption, contribution, and creation of brand-related social media content. Additionally, the analysis portrait 5 subtypes of consumers according to their behavior. This study has incremental explanatory power over preceding consumer brand engagement studies, in that it demonstrates how to manage brand equity to factually engage consumers into social media brand-related activities, therefore, generating valuable insights that may be used to support business.