A Survey of Recommendation Algorithms

Abstract

Recommender system can be defined as the subclass of information filtering system which attempts to give the guidance to the users regarding the useful services based on their personalized preferences, past behavior or based on their similar likings with other users. The various approaches of recommendation systems, like content-based, collaborative filtering, hybrid, etc, can further be classified according to their algorithmic technique as memory-based (heuristic) or model-based recommendation algorithms. Service recommender systems provides appropriate recommendations of services like movies, hotels, gadgets, etc, leading to an increase in the amount of data on the web, known as Big Data. It is becoming difficult to capture, store, manage and analyze such big data that affects the service recommender systems with issues like scalability and inefficiency. Also many existing service recommender system provides the same recommendations to different users based on ratings and rankings only, without considering the taste and preference of an individual user. This paper presents a survey on various recommendation algorithms, elaborating all its types along with its drawbacks. The paper also focuses on the solutions to overcome these drawbacks and provide apt recommendations to the users. It also deals with the solution to provide apt recommendations of the services to the users in big data environment. The issues of scalability and inefficiency while managing big data can be solved by using a distributed computing platform known as Hadoop.