Embeddings! Embeddings everywhere! - How to build a recommender system using representation learning.
Recommender systems are the major source of income of modern e-commerce. In this talk we will describe a large scale (over 90 millions items and 20 million registered users) e-commerce recommender system used at Allegro. The system is composed of two main parts: learning item representations and finding nearest neighbours. We will share the experience we gained from building the system.