Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction

TL;DR

This paper introduces the Learned Ranking Function (LRF), a system that directly optimizes long-term user satisfaction by transforming short-term behavior predictions into optimized recommendation slates, demonstrated on YouTube.

Contribution

It proposes a novel slate optimization approach with a constraint algorithm for multi-objective trade-offs, improving long-term user satisfaction over heuristic methods.

Findings

Successful deployment on YouTube

Live experiments show improved user satisfaction

Novel constraint optimization algorithm

Abstract

We present the Learned Ranking Function (LRF), a system that takes short-term user-item behavior predictions as input and outputs a slate of recommendations that directly optimizes for long-term user satisfaction. Most previous work is based on optimizing the hyperparameters of a heuristic function. We propose to model the problem directly as a slate optimization problem with the objective of maximizing long-term user satisfaction. We also develop a novel constraint optimization algorithm that stabilizes objective trade-offs for multi-objective optimization. We evaluate our approach with live experiments and describe its deployment on YouTube.