From the course: Building Recommender Systems with Machine Learning and AI

Unlock this course with a free trial

Join today to access over 22,400 courses taught by industry experts.

Bleeding edge alert: Deep factorization machines

Bleeding edge alert: Deep factorization machines - Python Tutorial

From the course: Building Recommender Systems with Machine Learning and AI

Bleeding edge alert: Deep factorization machines

- It's time for another bleeding edge alert. This is where we talk about some recent research that has promising results but hasn't made it into the mainstream with recommender systems yet. If you remember back to the matrix factorization section of this course, we mentioned factorization machines toward the end of it. They are a more general form of matrix factorization and can be designed to do the same thing as SVD as an example. But they take in categorical data, and can find latent relationships between any combination of the features they are given. As such, factorization machines are more general purpose than SVD and can sometimes find relationships between features that SVD wouldn't have considered. The idea of deep factorization machines is to combine the power of factorization machines with the power of deep neural networks to create an even more powerful recommender system. This hybrid approach outperforms factorization machines or neural networks used individually, albeit,…

Contents