A hybrid big data movies recommendation model based k-nearest neighbors and matrix factorization

On the subject of broadcasting the information, finding someone’s favorite book or movie in a sea of data containing books and movies has become a crucial issue. In an era when there are so many genres and types of movies and books, the customer may find it difficult to choose which to discover in the first place. Thus, personalized recommendation systems play an important role because of the value that is attributed to movies and books nowadays, and considering that there are so many to choose from that the user may not be able to have a specific target. In this context, our proposed work, design and implement a prototype of movie recommendation system while taking into consideration the real requirement for the search of movies and books. The research of movie recommendation system by using the k-nearest neighbors approach and collaborative filtering algorithm are adopted to extract the criteria for a good use case on recommender systems. At last, the results are as what was expected as they showed that the system has a good recommendation effect.