Homophily and Customer Influence

Teri Gibbs

During Wednesday's class, Professor Zak introduced the idea of "homophily," to emphasize the idea that it is beneficial to have a customer base that is similar to you in preference, race, or gender. For my social venture, I want to provide services to low income neighborhoods, which mostly include Blacks and Hispanics like myself. I wanted to delve deeper into the concept of homophily in order to maximize my customer reach, so I searched for articles that elaborated on growing businesses through strategic customer influence. As a result of my search, I found an article written by CMU's Dean of the Heinz College, Ramayya Krishnan, and two of his colleagues from the Tepper School of Business, Liye Ma and Alan Montgomery. The article titled, "Homophily or Influence? An Empirical Analysis of Purchase within a Social Network," describes how company's profitability can improve by 4-21% by manipulation social networks. The growth in profitability resulted from customers within a social network influencing another member's product choice and the length of that member's decision to buy a product. Below I have included the abstract from the article:

Abstract
Consumers that are close to one another in a social network are known to have 
similar behaviors. The focus of this study is the extent to which such observed 
similarity is driven by homophily or social influence. Homophily refers to the 
similarity in product preferences between individuals who are connected. Social 
influence is the dependence of consumers’ purchase decisions on their 
communication with others. We construct a hierarchical Bayesian model to study 
both the timing and choice of consumer purchases within a social network. Our 
model is estimated using a unique social network dataset obtained from a large 
Indian telecom operator for the purchase of caller ringer-back tones. We find 
strong social influence effects in both the purchase-timing and product-choice 
decisions of consumers. In the purchase-timing decision, we find that consumers 
are three times more likely to be influenced by network neighbors than by other 
people. In the product-choice decision we find a strong homophily effect. We show 
that ignoring either homophily or social influence will result in overestimated 
effects of the other factor. Furthermore, we show that detailed communication data 
is crucial for measuring influence effect, and influence effect can be either over- or 
underestimated when such data is not available. Finally, we conduct policy 
simulations on a variety of target marketing schemes to show that promotions 
targeted using network information is superior. For example, we find a 4-21% 
improvement on purchase probability, and an 11-35% improvement for promoting 
a specific product. 

Here is the link to the research study: http://community.mis.temple.edu/seminars/files/2011/02/krishnan-homophily-influence.pdf

Question: In what ways can you relate to your customer base? How will you use those qualities to more effectively market your service or product?