A new recommendation algorithm for reducing dimensionality and improving accuracy
Badr Ait Hammou, Ayoub Ait Lahcen, Driss Aboutajdine · 2016
Recommender systems are valuable tools for providing suitable recommendations to users. In the last decade, the amount of online information have grown rapidly. Consequently, traditional recommender systems often raise some limitations like inefficiency problems when processing or analysing such large volume of data. Matrix factorization is one of the most popular techniques for prediction problems in the fields of intelligent systems and data mining. It has shown its effectiveness in many real-world applications such as recommender systems. This paper describes a new algorithm that represents a solution to overcome the problem of high dimensionality when using matrix factorization for recommendation. It aims at producing low dimensional representation of data and more accurate predictions. The experimentation results show that the proposed algorithm significantly improves the accuracy of recommender systems over existing approaches.