One of the biggest challenges facing people new to building recommender systems is the lack of understanding around what these systems look like in the real world. The majority of the online content around recommender systems focuses on models and is often limited to a simple example of collaborative filtering. For new practitioners, there is an enormous gap between examples of simple models and a production system that serves recommendations. In this blog post we'll share a pattern that we feel covers the majority of recommender systems deployed today with examples from companies like Meta, Netflix, and Pinterest. This pattern is central to how we think about building end-to-end recsys within the NVIDIA Merlin team and we're excited to share it with the broader community and help build an understanding and consensus of what recommender systems (not just models) look like in production.

Our engineers are tasked with showing the right idea to the right user at the right time across home feed, search, Related Pins and more. Engineers use shared Pin features and user attributes to make more than 10B recommendations every day. Because multiple teams use the same data pipelines and frameworks, it's important that models can be used consistently in both a development environment and in production. Before, teams created separate processes for developing machine learning (ML) models. As these models became more complex, and teams increasingly had similar needs for a model development workflow, we needed a common language to express, evaluate and deploy models across multiple teams.

One of the most popular ways people find ideas on Pinterest is through Related Pins, an item-to-item recommendations system that uses collaborative filtering. Previously, candidates were generated using board co-occurrence, signals from all the boards a Pin is saved to. Now, for the first time, we're applying deep learning to make Related Pins even more relevant. Ultimately, we developed a scalable system that evolves with our product and people's interests, so we can surface the most relevant recommendations through Related Pins. In this post, we'll cover how we use deep learning to generate recommendation candidates, which, in testing, has increased engagement with Related Pins by 5 percent.

Pinterest today is announcing that it's now using a type of artificial intelligence called deep learning to recommend Related Pins, one of the most important features of its app for saving images and other content to boards. Related Pins, which appear below pins on Pinterest's web and mobile apps, are what they sound like -- pins that Pinterest thinks are related to the current one. This builds on Pinterest's use of deep learning -- which generally involves training artificial neural networks on lots of data, such as pictures, and then getting them to make inferences about new data -- for visual search, which lets users select regions of images and then find visually similar pins on Pinterest. Deep learning also lets Pinterest users tap on dots that appear above objects in an image to find pins with similar objects. Pinterest has experimented with using deep learning for Related Pins as far back as mid-2015.

I find myself being summoned from various directions, as if I've just stepped into a party with my closest friends. Many pins I see are interesting to me -- it's a pleasant feeling. A house with a window lined with dark brown wooden shutters. A shelf made from the back of an iMac. A media console on wheels with iron legs and wooden slats.

I find myself being summoned from various directions, as if I've just stepped into a party with my closest friends. Many pins I see are interesting to me -- it's a pleasant feeling. A house with a window lined with dark brown wooden shutters. A shelf made from the back of an iMac. A media console on wheels with iron legs and wooden slats.