A recommender system is a subclass of an information filtering system that looks to predict the rating or preference that users usually provide for an item. The concept of recommender systems has become very common in recent years subsequently being applied in different applications.

The most popular ones are probably products (for example, movies, music, books, research articles, news, search queries, social tags, and so on). Recommender systems can be classified into the following four categories typically:

• Collaborative filtering, also referred to as social filtering that filters information by using the recommendations of other people. The thing is people who agreed in their evaluation of certain items in the past are likely to agree again in the future. Therefore, a person who wants to see a movie for example, might ask for recommendations from his/her friends. Now once he received the recommendations from some of his/her friends who have similar interests, are trusted more than recommendations from others. This information is used in the decision on which movie to see.
• Content-based filtering (also known as cognitive filtering), which recommends items based on a comparison between the content of the items and a user profile. The content of each item is represented as a set of descriptors or terms, typically the words that occur in a document. The user profile is represented with the same terms and built up by analyzing the content of items that have been seen by the user. However, while implementing these types of recommendation systems, some issues that need to be considered are as follows:
  • First, terms can be assigned automatically or manually. For automatic assignment, a method has to be chosen so that these items can be extracted from the item list. Second, terms have to be represented in a way so that both the user profile and the items can be compared in a meaningful way. The learning algorithm itself has to be chosen wisely so that it's going to be able to learn a user profile based on already observer (that is, seen) items and makes appropriate recommendations based on this user profile. Content-based filtering systems are mostly used with text documents, where term parsers are used to select single words from the documents. The vector space model and latent semantic indexing are two methods that use these terms to represent documents as vectors in a multidimensional space. Furthermore, it is also used in relevance feedback, genetic algorithms, neural networks, and the Bayesian classifier for learning a user profile.
• A hybrid recommender system is a recent research and hybrid approach (that is, combining collaborative filtering and content-based filtering). Netflix is a good example of such a recommendation system that uses the Restricted Boltzmann Machines (RBM) and a form of the matrix factorization algorithm for large movie database like IMDb (see more at https://pdfs.semanticscholar.org/789a/d4218d1e2e920b4d192023f840fe8246d746.pdf). This recommendation which simply recommends movies, dramas, or streaming by comparing the watching and searching habits of similar users, is called rating prediction.
• Knowledge-based systems, where knowledge about users and products is used to reason what fulfills a user's requirements, using perception tree, decision support systems, and case-based reasoning.

In this chapter, we will discuss the collaborative filtering based recommender system for the movie recommendations.