ABSTRACT
Movie streaming services like Netflix, Hulu, Amazon Prime, and others are increasingly used by consumers to discover video content. For example, in 2017 Netflix subscribers collectively watched more than 140 million hours per day and Netflix surpassed $11 billion in revenue in 2017. Undoubtedly, movie streaming services have become an integral part of how we consume video content today, and the importance of movie recommendation systems cannot be understated—they are an integral part of how we consume video content. This chapter discusses the most popular approaches for collaborative filtering. These methods work by computing neighborhoods of similar users or items. The chapter proposes a deep learning approach for collaborative filtering based on an autoencoder. It demonstrates that the approach outperforms the neighborhood-based baseline. Deep learning, which is essentially just deep artificial neural networks, is able to learn complex decision boundaries for classification or complex non-linear regressions.
