Recommendation System Using Content Based Filtering for E commerce

Abstract

Recommender Systems are new generation internet tool that help user in navigating through information on the internet and receive information related to their preferences. The main goal is to propose a framework for recommendation system using content based filtering for e-commerce. Predictive models will use the products information and user information as sources of data which will be compared based on various parameters and the most appropriate product will be recommended. It is a user specific model. These models, in turn, will allow the system the decision of ordering a set of items according to their predicted usefulness. To show the validity and feasibility of our approach, a prototype application has been built, that implements solutions to the recommendation problem from different standpoints: identification of the data sources, inference based on similarity of items and user, recommending the most valued product and also updating the model from time to time.