Related Pins at Pinterest: The Evolution of a Real-World Recommender System
It provides practical insights for engineers building large-scale recommender systems, though it is incremental as it focuses on system evolution rather than novel algorithmic breakthroughs.
The paper presents a longitudinal study of Pinterest's Related Pins recommender system, which powers over 40% of user engagement, detailing its evolution from prototypes to a complex web-scale system while addressing challenges like feedback loops and performance evaluation.
Related Pins is the Web-scale recommender system that powers over 40% of user engagement on Pinterest. This paper is a longitudinal study of three years of its development, exploring the evolution of the system and its components from prototypes to present state. Each component was originally built with many constraints on engineering effort and computational resources, so we prioritized the simplest and highest-leverage solutions. We show how organic growth led to a complex system and how we managed this complexity. Many challenges arose while building this system, such as avoiding feedback loops, evaluating performance, activating content, and eliminating legacy heuristics. Finally, we offer suggestions for tackling these challenges when engineering Web-scale recommender systems.