Predicting trading interactions in an online marketplace through location-based and online social networks

Link prediction is a prominent research direction e.g., for inferring upcoming interactions to be used in recommender systems. Although this problem of predicting links between users has been extensively studied in the past, research investigating this issue simultaneously in multiplex networks is rather rare so far. This is the focus of this paper. We investigate the extent to which trading interactions between sellers and buyers within an online marketplace platform can be predicted based on three different but overlapping networks—an online social network, a location-based social network and a trading network. In particular, we conducted the study in the context of the virtual world Second Life. For that, we crawled according data of the online social network, user information of the location-based social network obtained by specialized bots, and we extracted purchases of the trading network. Overall, we generated and used 57 topological and homophilic features in different constellations to predict trading interactions between user pairs. We focused on both unsupervised as well as supervised learning methods. For supervised learning, we achieved accuracy values up to (Formula presented.), for unsupervised learning we obtained nDCG values up to over (Formula presented.) and MAP values up to (Formula presented.).