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
Recommendations Engines position themselves to amass power
The profit is not in the growing the food, or the transporting the food, or the preparing the food, or the serving the food, or the cleaning the dishing and restaraunt, but in shaping the decisions of customers. The profit is not to the driver but to Uber, who runs the platform.