A Deep Learning Approach towards Cold Start Problem in Movie Recommendation System

Abstract

Recommendation systems play an important role for e-commerce websites to make profits. It has a variety of applications in different domains. There are three types of categories in which recommendation systems are classified i.e. content based, collaborative and hybrid systems. These systems suffer when a redundant amount of information is not available to provide recommendations. This problem is known as the cold start problem. In this digital era, it is possible to collect meta information about a user and provide rich recommendations. Various approaches such as social media analysis, graph networks have been proposed to solve this problem. But they lack personalization and generate irrelevant recommendations affecting the system performance. The objective of this work is to resolve new user cold start problem in movie recommendation systems using a deep learning approach that utilizes demographic attributes to cluster similar users. This embedding is given to the deep neural network to generate the recommendations. From the analysis done, we verify the effectiveness of our approach..