Machine Learning Times
Machine Learning Times
Elon Musk Predicts Artificial General Intelligence In 2 Years. Here’s Why That’s Hype
 Originally published in Forbes, April 10, 2024 When OpenAI’s...
Survey: Machine Learning Projects Still Routinely Fail to Deploy
 Originally published in KDnuggets. Eric Siegel highlights the chronic...
Three Best Practices for Unilever’s Global Analytics Initiatives
    This article from Morgan Vawter, Global Vice...
Getting Machine Learning Projects from Idea to Execution
 Originally published in Harvard Business Review Machine learning might...

1 year ago
Blueprints for Recommender System Architectures: 10th Anniversary Edition

Originally published in Amatriain, Jan 29, 2023.

Ten years ago, we published a post in the Netflix tech blog explaining our three-tier architectural approach to building recommender systems (see below). A lot has happened in the last 10 years in the recommender systems space for sure. That’s why, when a few months back I designed a Recsys course for Sphere, I thought it would be a great opportunity to revisit the blueprint.

In this blog post I summarize 4 existing architectural blueprints, and present a new one that, in my opinion, encompasses all the previous ones.

At a very high-level, any recommender system has items to score and/or rank, and a machine learned model that does that. This model needs to be trained on some data, which is obtained from the service where the recommender operates in some form of feedback loop. The architectural blueprints that we will see below connect those components (and others) in a general way while incorporating some best practices and guidelines.

The Netflix three tier architecture

In our post ten years ago, we focused on clearly distinguishing the components that can be executed offline (i.e. not when the recommendations need to be served but rather e.g. once a day), those that need to be computed online (i.e. when the user visits the site and the recommendation is being served) and those somewhere in the middle called nearline (i.e. components that are executed when the user visits the site, but do not need to be served in real-time). At that time, and still today in many cases, most of the big data training of the algorithm was performed offline using systems such as Hadoop or Spark. The nearline layer included things like filtering in response to user events, but also some retraining capabilities such as e.g. folding-in and incremental matrix factorization training (see here for a practical introduction to the topic).

To continue reading this article, click here.

8 thoughts on “Blueprints for Recommender System Architectures: 10th Anniversary Edition

  1. It’s interesting to see how technology and the field of recommendation systems have evolved over the past decade. The clear distinction between offline, nearline, and online components that you mentioned is still relevant today. However, the way in which these components are executed and the tools used have changed. Affiliate Marketing SEO

  2. The article highlights the significance of the book “Blueprints for Recommender Systems” in the field of data science and machine learning, particularly for building recommender systems. The book’s practical approach and comprehensive coverage make it a valuable resource for professionals and researchers interested in this area.

    headstone engraving


Leave a Reply