Reducing Data Sparsity in Movie Recommendation System

Recommendation plays a crucial part in our digital life. When there are no recommendations, getting disoriented in a sea of data is accessible. In massive data sets, the recommendation system (RS) has proven to be an effective information filtering tool, minimizing the information overload experienced by Web users. Collaborative filtering (CF) provides recommendations to the currently active user without first reviewing the content of the information resource. These suggestions or recommendations are based on a lot of user history data. In recent years, it has been seen a decline in the performance of collaborative filtering-based recommendation systems due to a need for more data and a large amount of information. Movies or films, as highly significant entertainment, are usually suggested and endorsed to us by other people. Each individual enjoys a specific kind or sub-genre of film. Most websites like Netflix and IMDB are operating based on recommendations. The only issue that may fail the recommendation system is the difficulty caused by sparsity. In this paper, a new approach will be discussed that has the potential to tackle the problem of sparsity.