Long-run User Value Optimization in Recommender Systems through Content Creation Modeling

TL;DR

This paper presents a machine learning approach to optimize long-term user value in recommender systems by estimating content producers' potential to generate future user engagement, using A/B testing and heterogeneous effects modeling.

Contribution

It introduces a novel method for long-run user value optimization in recommender systems through discounted utility maximization and content creation modeling.

Findings

Effective estimation of long-term user value using heterogeneous effects models.

Application of the method in Facebook's feed ranking system.

Potential for broader use in various recommender systems.

Abstract

Content recommender systems are generally adept at maximizing immediate user satisfaction but to optimize for the \textit{long-run} user value, we need more statistically sophisticated solutions than off-the-shelf simple recommender algorithms. In this paper we lay out such a solution to optimize \textit{long-run} user value through discounted utility maximization and a machine learning method we have developed for estimating it. Our method estimates which content producers are most likely to create the highest long-run user value if their content is shown more to users who enjoy it in the present. We do this estimation with the help of an A/B test and heterogeneous effects machine learning model. We have used such models in Facebook's feed ranking system, and such a model can be used in other recommender systems.