A COLLABORATIVE FILTERING-BASED RECOMMENDER SYSTEM ALLEVIATING COLD START PROBLEM

Abstract

Consumers currently have a surplus of items available to purchase via online stores. Surplus of goods enables users to have huge variety but it often leads to inconvenience for users. Consumers have to spend a lot of time going through items to find goods of their preference. To automate the process of sharing relevant suggestions, recommender systems are used.

Recommender systems are making their presence felt in a number of domains, be it for ecommerce or education, social networking etc. With huge growth in number of consumers and items in recent years, recommender systems face some key challenges. These are: producing high quality recommendations and performing many recommendations per second for millions of consumers and items. New recommender system technologies are needed to scale themselves for new items as well as in new user in the system in order to get high quality recommendations. In this thesis, we focus on collaborative approach-based recommender systems to solve the issue of cold start problem. We have compared multiple algorithms which aim to solve cold start problem and proposed a new hybrid algorithm. This new algorithm is implemented on Movie-Lens 1Million Dataset.