Bridging social media to E-Commerce: Using collaborative filtering product recommendation

Abstract

Numerous online business sites bolster the component of social login where clients can sign on the sites utilizing their interpersonal organization personalities, for example, their Facebook or Twitter accounts. Clients can likewise post their recently obtained items on micro blogs with connections to the internet. We propose a novel answer for cross-site cold start item suggestion which expects to prescribe items from web based business sites to clients at long range interpersonal communication destinations in “cold start” circumstances, a issue which has once in a while been investigated some time recently. A noteworthy point in this paper is friend request module and similar life style grouping and also the product recommendation during cold start situation. In particular, we propose learning both clients' and items' component portrayals (called client embeddings and item embeddings, separately) from information gathered from online business sites.