Minimizing Live Experiments in Recommender Systems: User Simulation to Evaluate Preference Elicitation Policies

TL;DR

This paper presents a simulation-based approach to evaluate preference elicitation policies in recommender systems, reducing reliance on costly live experiments by using robust user behavior models and a simulation platform.

Contribution

It introduces a counterfactually robust simulation methodology for evaluating onboarding algorithms, specifically applied to YouTube Music, enhancing evaluation efficiency and reliability.

Findings

Simulation accurately predicts live deployment performance.

Reduced need for costly real-user experiments.

Effective evaluation of preference elicitation algorithms.

Abstract

Evaluation of policies in recommender systems typically involves A/B testing using live experiments on real users to assess a new policy's impact on relevant metrics. This ``gold standard'' comes at a high cost, however, in terms of cycle time, user cost, and potential user retention. In developing policies for ``onboarding'' new users, these costs can be especially problematic, since on-boarding occurs only once. In this work, we describe a simulation methodology used to augment (and reduce) the use of live experiments. We illustrate its deployment for the evaluation of ``preference elicitation'' algorithms used to onboard new users of the YouTube Music platform. By developing counterfactually robust user behavior models, and a simulation service that couples such models with production infrastructure, we are able to test new algorithms in a way that reliably predicts their performance on key metrics when deployed live. We describe our domain, our simulation models and platform, results of experiments and deployment, and suggest future steps needed to further realistic simulation as a powerful complement to live experiments.