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

Unlock this course with a free trial

Join today to access over 22,600 courses taught by industry experts.

Bleeding edge alert: Translation-based recommendations

Bleeding edge alert: Translation-based recommendations - Python Tutorial

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

Start my 1-month free trial Buy for my team

Bleeding edge alert: Translation-based recommendations

“

- [Instructor] 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. I want to mention an interesting paper from the 2017 conference on recommender systems. It's called Translation-based Recommendations, and it comes from a team at the University of California at San Diego. If you want to check out the original paper as well as the data and code behind it, you can find it at this link. The idea behind it is that users are modeled as vectors moving from one item to another in a multidimensional space. And you can predict sequences of events, like which movie a user is likely to watch next, by modeling these vectors. The reason this paper is exciting is because it outperformed all of the best existing methods for recommending sequences of events in all but one case and one data set. And I also like that they measure their results based on hit rate instead…

Contents