English

Learning to Rank in the Position Based Model with Bandit Feedback

Machine Learning 2020-04-29 v1 Machine Learning

Abstract

Personalization is a crucial aspect of many online experiences. In particular, content ranking is often a key component in delivering sophisticated personalization results. Commonly, supervised learning-to-rank methods are applied, which suffer from bias introduced during data collection by production systems in charge of producing the ranking. To compensate for this problem, we leverage contextual multi-armed bandits. We propose novel extensions of two well-known algorithms viz. LinUCB and Linear Thompson Sampling to the ranking use-case. To account for the biases in a production environment, we employ the position-based click model. Finally, we show the validity of the proposed algorithms by conducting extensive offline experiments on synthetic datasets as well as customer facing online A/B experiments.

Keywords

Cite

@article{arxiv.2004.13106,
  title  = {Learning to Rank in the Position Based Model with Bandit Feedback},
  author = {Beyza Ermis and Patrick Ernst and Yannik Stein and Giovanni Zappella},
  journal= {arXiv preprint arXiv:2004.13106},
  year   = {2020}
}
R2 v1 2026-06-23T15:08:07.725Z