ANALYSIS OF ALGORITHMS TO COUNTER LONG TAIL ISSUE IN RECOMMENDER SYSTEM

Abstract

Today’s world is all about information, with most of it online which enables anytime, anywhere, easy and unlimited access; participation & publishing of information has consequently escalated the suffering of ‘Information Glut’. Such increase in data leads to information overload, thus creating a high level of stress and chaos. So, as to save the person from this misperception and in order to make the surfing practice better, RS was introduced. Assisting users’ informational searches with reduced reading or surfing time by extracting and evaluating accurate, authentic & relevant information are the primary concerns in the present milieu. The recommendation system is defined as the software technology/tools that make relevant suggestions to a user. Nowadays, the most prominent problem while making a recommender system is a cold start and long tail problem. Where we deal with new and rare data items thus creating sparsity in the dataset. Which in turns leads to suggesting same items to the user again and again. Thus, there's a great need in dealing and evaluating various algorithms to leverage long tail recommender system. The long Tail problem happens when we deal with relatively rare item set. It is a persistent version of cold start problem. To leverage it, four different algorithms to compare and contrast long tail issue in Recommender system have been studied and implemented.