Abstract

How can we build and optimize a recommender system that must rapidly fill slates of personalized recommendations? The combination of deep learning stacks with fast maximum inner product search (MIPS) algorithms has shown that it is possible to deploy flexible models in production that can rapidly deliver personalized recommendations to users. Albeit promising, this methodology is not sufficient to build a recommender system that maximizes the reward, such as the probability of click. This tutorial takes participants through the necessary steps to model the reward and directly optimize the reward of recommendation engines built upon fast search algorithms to produce high-performance reward-optimizing recommender systems.

Citation