arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.05138cs.LGcs.IRstat.ML
收藏

学习产品排名对虚假用户的鲁棒性

Learning Product Rankings Robust to Fake Users

MIT Sloan School of Management, Massachusetts Institute of Technology(麻省理工学院斯隆管理学院);Yale School of Management, Yale University(耶鲁大学管理学院);Google Research(谷歌研究院);Department of Management, University of Toronto Scarborough and Rotman School of Management(多伦多大学士嘉堡分校管理系与罗特曼管理学院)

Negin Golrezaei, Vahideh Manshadi, Jon Schneider, Shreyas Sekar

摘要:

在许多在线平台中,客户的决策受到产品排名的重大影响,因为大多数客户只检查少数排名靠前的产品。同时,这些平台还使用与客户行为相对应的相同数据来了解这些产品必须如何排名或订购。然而,底层学习过程中的这些互动可能会激励卖家通过雇用虚假用户人为地夸大自己的地位,点击农场的出现就是一个例子。出于这种欺诈行为的动机,我们研究了一个平台的排名问题,该平台面临着真实和虚假用户的混合,这些用户彼此无法区分。我们首先表明,现有的学习算法-在没有假用户的情况下是最优的-可能会收敛到高度次优的排名下操纵假用户。为了克服这一缺陷,我们在两种信息环境下开发了高效的学习算法:在第一种设置中,平台知道虚假用户的数量,而在第二种设置中,它不知道虚假用户的数量。对于这两种环境,我们证明了我们的算法收敛到最优排名,同时对上述欺诈行为具有鲁棒性;我们还为我们的方法提供了最坏情况下的性能保证,并表明它们显著优于现有算法。在高层次上,我们的工作采用了几种新的方法来保证鲁棒性,例如:(i)构建产品排序图,对从客户行为推断的产品之间的成对关系进行编码;以及(ii)实现多层次的学习,并在各级之间进行明智的双向交叉学习。

英文摘要:

In many online platforms, customers' decisions are substantially influenced by product rankings as most customers only examine a few top-ranked products. Concurrently, such platforms also use the same data corresponding to customers' actions to learn how these products must be ranked or ordered. These interactions in the underlying learning process, however, may incentivize sellers to artificially inflate their position by employing fake users, as exemplified by the emergence of click farms. Motivated by such fraudulent behavior, we study the ranking problem of a platform that faces a mixture of real and fake users who are indistinguishable from one another. We first show that existing learning algorithms---that are optimal in the absence of fake users---may converge to highly sub-optimal rankings under manipulation by fake users. To overcome this deficiency, we develop efficient learning algorithms under two informational environments: in the first setting, the platform is aware of the number of fake users, and in the second setting, it is agnostic to the number of fake users. For both these environments, we prove that our algorithms converge to the optimal ranking, while being robust to the aforementioned fraudulent behavior; we also present worst-case performance guarantees for our methods, and show that they significantly outperform existing algorithms. At a high level, our work employs several novel approaches to guarantee robustness such as: (i) constructing product-ordering graphs that encode the pairwise relationships between products inferred from the customers' actions; and (ii) implementing multiple levels of learning with a judicious amount of bi-directional cross-learning between levels.

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。

↑