Modeling Choice Interdependence in a Social Network

Abstract

This paper investigates how individuals' product choices are influenced by the product choices of their connected others and how the influence mechanism may differ for fashion- versus technology-related products. We conduct a novel field experiment to induce and observe choice interdependence in a closed social network. In our experiment, we conceptualize individuals' choices to be driven by multiattribute utilities, and we measure their initial attribute preferences prior to observing their choice interdependence and collecting network information. These design elements help alleviate concerns in identifying social interaction effects from other confounds. Given that we have complete information on choices and their sequence, we use a discrete-time Markov chain model. Nonetheless, we also use a Markov random field (MRF) model as an alternative when the information on choice sequence is missing. We find significant social interaction effects. Our findings show that whereas experts exert asymmetrically greater influence on a technology-related product, popular individuals exert greater influence on a fashion-related product. In addition, we find choices made by early decision makers to be more influential than choices made later for the technology-related product. Finally, using the MRF with snapshot data can also provide good out-of-sample predictions for a technology-related product.

The Impact of Social Media on Learning Behavior for Sustainable Education: Evidence of Students from Selected Universities in Pakistan

“…In social media, influential people are typically those exerting strong influences on peers to change their behavior, attitudes, and interaction [130,131]. Social computing facilitates social influencing behavioral research, and it is concerned with social behavior [132]. The analysis of a social network is a popular technique to assess social media users' social influence identification [133][134][135].…”

College Choice as a Collective Decision

“…Conjoint analysis has been previously used in the marketing literature to model joint choice (Krishnamurthi ). A line of work by Aribarg and coauthors (Aribarg, Arora, and Kang ; Aribarg, Arora, and Onur Bodur ; Wang, Aribarg, and Atchadé ) uses conjoint analysis to identify a joint choice model in which learning another's preferences leads one to revise their own. Even within a more standard economic framework of bargaining problems where preferences are constant, conjoint analysis allows for a straightforward way of identifying a rather difficult model in order to understand important facts about parent and student preferences and how they might fit together to form a household decision.…”

Being Active in Online Communications: Firm Responsiveness and Customer Engagement Behaviour

“…This theory posits that the social influence created by online traffic and the propagated information in a social network is pervasive in shaping individuals' attitudes, cognition and behaviour (Iyengar et al, 2011;Kurt et al, 2011). Management researchers regard such social influence among fellow consumers as one of the primary factors affecting consumers' choices of products (e.g., Kurt et al, 2011;Wang et al, 2013), purchase intentions (e.g., Fang et al, 2013;Zhang et al, 2014), perception (e.g., Cheng & Ho, 2015; Lee et al, 2015), and online communication behaviour (e.g., Goes et al, 2014;Sridhar & Srinivasan, 2012;Zhang et al, 2011). A wider scope of customer engagement can amplify the crowd's voice on the internet and hence strengthen the social influence, with a greater number of customers acting and participating in the network (King et al, 2014).…”