arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.13106cs.LGstat.ML
收藏

基于位置的Bandit反馈模型的学习排序

Learning to Rank in the Position Based Model with Bandit Feedback

Amazon(亚马逊)

Beyza Ermis, Patrick Ernst, Yannik Stein, Giovanni Zappella

摘要:

个性化是许多在线体验的关键方面。特别是,内容排名通常是提供复杂个性化结果的关键组件。通常,应用监督学习排名方法,其遭受在负责产生排名的生产系统的数据汇集期间引入的偏差。为了弥补这个问题,我们利用上下文多武装匪徒。我们提出了新的扩展两个著名的算法,即LinUCB和线性汤普森采样的排名用例。为了解释生产环境中的偏差,我们采用了基于位置的点击模型。最后,我们通过在合成数据集上进行广泛的离线实验以及面向客户的在线A/B实验来证明所提出的算法的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑