Social Networking Sites for Cross-Site Cold-Start Product Recommendation

Abstract

— In recent years, the boundaries between e-commerce and social networking became more and more
blurred. several e-commerce websites support the mechanism of social login wherever users will register the websites
victimization their social network identities like their Facebook or Twitter accounts. Users also can post their recent
purchased product on microblogs with links to the e-commerce product websites. throughout this paper we've
associate degree inclination to propose a singular account cross-site cold-start product recommendation, that aims to
advocate product from e-commerce websites to users at social networking sites in “coldstart” things, a tangle that has
seldom been explored before. an important challenge is that the due to leverage info extracted from social networking
sites for cross-site cold-start product recommendation. we've a bent to propose to use the coupled users across social
networking sites and e-commerce websites (users global organization agency have social networking accounts and
have created purchases on e-commerce websites) as a bridge to map users’ social networking decisions to a special
feature illustration for product recommendation. In specific, we've associate degree inclination to propose learning
each users’ and merchandises’ feature representations (called user embeddings and merchandise embeddings,
respectively) from information collected from e-commerce websites victimization continual neural networks therefore
apply a changed gradient boosting trees methodology to remodel users’ social networking decisions into user
embeddings. we've associate degree inclination to then develop a feature-based matrix resolution approach that may
leverage the learnt user embeddings for cold-start product recommendation. Experimental results on associate
oversized dataset product of necessary|the biggest} Chinese microblogging service SINA WEIBO and to boot the
foremost important Chinese B2C e-commerce computing device JINGDONG have shown the effectiveness of our
planned framework.