In modern E-Commerce it is not easy for the customers to find the best goods of their interest as there are millions of products available online. Recommendation systems are one of information filtering systems forecasting the items that may be additional interest for user within a big set of items on the basis of user’s interests. This System utilizes the Collaborative filtering, which offers a few recommendations to users on the basis of matches in behavioral and useful examples of users and furthermore demonstrates comparable affection and behavioral examples with those users. The paper presents an approach for Recommendation System to generate meaningful recommendations to a collection of users for items or products that might interest them. This approach uses weighted hybrid recommendation system which combines content based recommendation system and knowledge based recommendation system in order to increase the overall performance of the system. The main idea is using multiple recommendation techniques to suppress the drawbacks of the traditional techniques or an individual technique in a combined model. The paper presents a system to improve the accuracy of recommendation in big data application.