Minimizing Live Experiments in Recommender Systems: User Simulation to Evaluate Preference Elicitation Policies
Authors:
Preprint
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.Keywords
All Related Versions
- Version 1, 2024-09-26, ArXiv
- Published version: , 2925.
This publication has 9 references indexed in Scilit:
- Recommended for you: The Netflix Prize and the production of algorithmic cultureNew Media & Society, 2014
- A collaborative filtering approach to mitigate the new user cold start problemKnowledge-Based Systems, 2012
- Controlled experiments on the web: survey and practical guideData Mining and Knowledge Discovery, 2008
- Applying associative retrieval techniques to alleviate the sparsity problem in collaborative filteringACM Transactions on Information Systems, 2004
- Amazon.com recommendations: item-to-item collaborative filteringIEEE Internet Computing, 2003
- Finite-time Analysis of the Multiarmed Bandit ProblemMachine Learning, 2002
- Causality: Models, Reasoning and InferencePhilosophical Review, 2001
- Asymptotically efficient adaptive allocation rulesAdvances in Applied Mathematics, 1985
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982