Deep Learning Based Recommender Systems

Recommender Systems (RSs) are valuable and practical tools that help users to find interesting products in a large space of possible options. Many hybrid recommender systems combine collaborative filtering and content-based approach to build a more robust system. This paper aims to propose a new deep learning based recommender system to enhance recommendation performance and to overcome the limitations of existing approaches, especially when dealing with the cold start problem. So, a hybrid model based on Deep Belief Networks and item-based collaborative filtering is proposed. We conducted experiments on MovieLens 100K dataset. The results showed that our method outperforms existing hybrid recommender systems.