Who will trade with whom?: predicting buyer-seller interactions in online trading platforms through social networks

Christoph Trattner, Denis Parra, Lukas Eberhard, Xidao Wen

Abstract: In this paper we present the latest results of a recently started project that aims at studying the extent to which links between buyers and sellers, i.e. trading interactions in online trading platforms, can be predicted from external knowledge sources such as online social networks. To that end, we conducted a large-scale experiment on data obtained from the virtual world Second Life. As our results reveal, online social network data bears a significant potential (28% over the baseline) to predict links between buyers and sellers in online trading platforms.