Netflix is an American entertainment company founded by Reed Hastings and Marc Randolph on August 29, 1997, in Scotts Valley, California. It specializes in and provides streaming media, video-on-demand online, and DVD by mail. In 2013, Netflix expanded into film and television production, as well as online distribution. Netflix uses a model-based collaborative filtering approach for real-time movie recommendation for its subscribers.

In this chapter, we will see two end-to-end projects and develop a model for item-based collaborative filtering for movie similarity measurement and a model-based movie recommendation engine with Spark that recommends movies for new users. We will see how to interoperate between ALS and matrix factorization (MF) for these two scalable movie recommendation engines. We will use the movie lens dataset for the project. Finally, we will see how to deploy the best model in production.

In a nutshell, we will learn the following topics through two end-to-end projects:

• Recommendation system—how and why?
• Item-based collaborative filtering for movie similarity
• Model-based movie recommendation with Spark
• Model deployment