An Enhanced Method for Detecting Attack in Collaborative Recommender System

Abstract

In recent decades, the advent of digital information services by YouTube, Amazon, Netflix, and many other web services of this kind have made recommendation systems more and more ubiquitous in our lives. rice field. The system suggests and recommends articles to the user that may interest the user in online advertising (recommending and suggesting appropriate content to the user that matches the user’s tastes and activities). Recommendation systems have become an integral part of our daily online journeys. The quality of predictions is degraded by the attackers by injection of fake profiles. therefore, the shilling attacks detection are necessary. thus, various shilling attacks detection techniques proposed. In this paper, we introduce an enhanced technique for detecting shilling attacks in collaborative recommender system using supervised learning techniques. The proposed method results show that getting better accuracy when we employee ensemble learning algorithm.