A Novel Cross-Site Product Recommendation Method in Cold Start Circumstances

Abstract

In the last 20 years, more than 250 research articles were published about research paper recommender systems. In the recent years, the farthest point between internet business applications such as e-commerce websites and social networking applications has interpersonal communication and it has turned out to be progressively obscured. Numerous e-commerce web and mobile applications allowing social logging mechanism where their clients can signing in their websites using their personal social network identities such as twitter or Facebook accounts etc. users can likewise post their recently purchased items on social networking websites with the appropriate links to the e-commerce product web pages. In this paper, we propose a new solution to recommend products from e-commerce websites to users at social networking sites. a noteworthy issue is how to leverage knowledge from social networking websites when there is no purchase history for a customer, especially in cold start situations.in particular, we proposed the solution for cold start recommendation by linking the users to social networking sites and e-commerce websites i.e. customers who have social network identities and have purchased on e-commerce websites as a bridge to map user?s social networking features into another feature representation which can be easier for a product recommendation. Here we propose to learn by using recurrent neural networks both user?s and product?s feature representations called user embedding and product embedding from the data collected from e-commerce website and then apply a modified gradient boosting trees method to transform user?s social networking features into user embedding. Once found, then develop a feature-based matrix factorization approach which can leverage the learned user embedding for the cold-start product recommendation. Experimental results show that our approach effectively works and gives the best-recommended results in cold start situations.