Author(s): Mohammed Mehtab Siddique, Md Ateeq Ur Rahman
In recent years, the boundaries between e-commerce and social networking became progressively blurred. Several e-commerce websites backing the structure of social login wherever users like to sign into the websites deception their social network integrities like their Face- book or Twitter accounts. Users also can post their recent purchased product on micro blogs with links to the e-commerce product websites. During this paper we have a tendency to propose a unique answer for cross-site cold-start product recommended that aims to advocate product from e-commerce websites to users at social networking sites in “cold start” things, a haul that has seldom been explored before. A serious challenge is the way to leverage data extracted from social networking sites for cross-site cold-start product recommended. We come up the connected users across social networking sites and e-commerce websites (users United Nations agency have social networking accounts and have created purchases on e-commerce websites) as a bridge to map users’ social networking options to a different feature illustration for product recommended. In specific, we have a habit to propose learning each users’ and product’ feature representations (called user embedding’s and product embedding’s, respectively) from information collected from e-commerce websites victimization continual neural networks so apply a changed gradient boosting trees methodology to remodel users’ social networking options into user embedding’s. We have a tendency to then develop a feature-based matrix factorization approach which might leverage the learnt user embedding’s for cold-start product recommended. Experimental results on an oversized dataset made from the biggest Indian micro blogging service Flipkart.