A recommender system is an algorithm that makes personalized suggestions to users based on their past interactions with the software. The most famous example is the "customers who bought X also bought Y" type of recommendation on Amazon and other e-commerce websites.
In the past few years, recommender systems have gained a lot of importance: it has become clear for the online businesses that the better the recommendations they give on their websites, the more money they make. This is why today almost every website has a block with personalized recommendations.
In this chapter, we will see how we can use TensorFlow to build our own recommender system.
In particular, we will cover the following topics:
- Basics of recommender systems
- Matrix Factorization for recommender systems
- Bayesian Personalized Ranking
- Advanced recommender systems...
