An Efficient Approach Based on Trust to Purge the Weekness of Recommendation System

Recommendations are the need of the hour in ecommerce sector. It allows user‟s to shop according to their desire. Finding similarity between users to recommend items is the common concept used in most of the collaborative recommendation system. However there are many problems like sparsity, recommending items to cold-start user and handling copy-profile attack(Shilling‟s attack).To overcome these setbacks we make use of trust and distrust statements and propose a novel method to increase the accuracy of recommended items.