An architecture of a web recommender system using social network user profiles for e-commerce

In this paper we propose a concept of a web e-com-merce system that collects and uses, in the process of making recommendations, data obtained from social network profiles of its users. This architecture modeling approach was developed within the project of a mashup Web application that integrates with Facebook API. We describe which data could be obtained from Facebook, propose the way to store it and suggest how the information from user profile could improve the effectiveness of a e-commerce recommender system.