Inferring Preference Correlations From Social Networks
Source: Hewlett-Packard (HP)
Identifying consumer preferences is a key challenge in customizing electronic commerce sites to individual users. The increasing availability of online social networks provides one approach to this problem: people linked in these networks often share preferences, allowing inference of interest in products based on knowledge of a consumer's network neighbors and their interests. This paper evaluates the benefits of inference from online social networks in two contexts: a random graph model and a web site allowing people to both express preferences and form distinct social and preference links. The paper determines conditions on network topology and preference correlations leading to extended clusters of people with similar interests.