Peer-Based Recommendations in Online B2C E-Commerce: Comparing Collaborative Personalization and Social Network-Based Personalization

With the widespread diffusion of social network platforms, e-vendors can now use social network information to provide personalized services to their consumers. Nonetheless, the accuracy of social network-based personalization remains uncertain, as compared to that of traditional personalization approaches. Drawing on social influence and similarity attraction theories, this study compares social network-based personalization with the traditional peer-based personalization approach of collaborative personalization. We report results of a preliminary within subject experiment of 29 subjects belonging to a single social network. Our findings indicate that social network-based personalization can provide accurate personalized offerings. These are as accurate as those of collaborative personalization when within the specific product category on which collaborative personalization is based and better than collaborative personalization when outside the specific category.