User Interaction Based Recommender System Using Machine Learning

In the present scenario of electronic commerce (E-Commerce), in-depth knowledge user interaction with resources has become a significant research concern that impacts more on analytical evaluations recommender systems. For staying in aggressive E-Commerce, various products and services regarding distinctive requirements must be provided time. Moreover, because large amount product information available online, Recommender Systems (RS) are required to analyze availability consumers, which improves decision-making customers detailed reduces time consumption. With note, this paper derives new model called User Interaction based System (UI-RS) utilizes data from multiple sources opinion-based analysis for sensing consumer needs interests. that, Content-Based Filtering (CBF) analyses determines likeliness recommend consumers. Then, is combined Dempster-Shafer (D-S) evidence theory, then, decision making recommendation performed CBF. modified Radial Basis Function Neural Networks (RBFNN) technique been incorporated measuring recommendations. The results show proposed produces better providing accurate recommendations Consumers higher rate coverage precision, thereby enhancing growth E-Commerce.