On deep neural network for trust aware cross domain recommendations in E-commerce

Over the years, cross-domain and trust-based recommendation systems are proven to be very helpful in solving issues pertaining to data sparsity and cold start. Many e-commerce sites used recommender systems as business tools for increasing their sale productivity and help their customers in finding suitable products. However, due to sparse rating and lack of historical information, such systems cannot generate effective recommendations. Matrix factorization and deep learning techniques have been the focus of research community for the last few years to solve the problem of data sparsity and cold start. In this paper, we have proposed a model called Trust Aware Cross-Domain Deep Neural Matrix Factorization (TCrossDNMF) that predicts rating of an item for an active user and solves user cold start problem in the cross-domain scenario of 'User Overlap' in e-commerce system. TCrossDNMF model is divided into four main steps: i) Features learning that learns the users' features using a latent factor model and then finds the similarity between users of source and target domains. As the users are shared between two domains, the proposed model learns the common information and transfers the knowledge from a source to target domain. ii) Ranking that finds set of similar users (neighbors), and then filters out the dissimilar users based on similarity threshold theta, and then generates a bipartite trust graph from these reduced set of users and executes Ant Colony Optimization, to find trustworthy neighbors for an active user. iii) Weighting computes the trust degree between an active user and his or her top-k neighbors. iv) Prediction that trains the TCrossDNMF model using multilayer perceptron (MLP) and generalized matrix factorization (GMF) by repre-senting user-item interactions in higher dimensions and ensembles the GMF and MLP with trust information for rating prediction. We evaluated proposed model on a real dataset collected from a popular e-commerce retail service 'AliExpress'. We used categories available in 'AliExpress' as source domain and a target domain. For observing the performance of proposed model, we took six domains that have a higher ratio of sparsity. The proposed model is evaluated by using MAE, RMSE and F-measure metrics and compared it with baselines. The experiments show that the proposed model is a viable solution for the mentioned problem with significant improvements in results.