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 1610.05604stat.MLmath.OCstat.ME
收藏

高维动态分类个性化

Dynamic Assortment Personalization in High Dimensions

Nathan Kallus, Madeleine Udell

摘要:

我们研究的问题,动态分类个性化与大,异质的人口和广泛的产品阵列,并证明了有效的,高效的大规模个性化的结构先验的重要性。分类个性化是为每个人(类型)选择产品,广告或其他产品(项目)的最佳分类的问题,以便最大化收入。这个问题是电子商务和在线广告收入管理的核心,其中项目和类型都可以达到数百万。我们制定的动态分类个性化的问题作为一个离散的上下文强盗$m$上下文(类型)和指数级的许多武器($n$项目的缩写)。我们假设每种类型的偏好都遵循一个带有$n$参数的简单参数模型。总之,有$mn$参数,现有文献表明,订单最佳后悔尺度为$mn$。然而,估计这么多参数所需的数据比大多数收入管理应用程序中可用的数据大几个数量级,并且这些模型下的最佳遗憾是不可接受的高。在本文中,我们对问题施加了一个自然的结构-一个小的潜在维度,或低秩。在静态设置中,我们表明,这个模型可以有效地学习,从令人惊讶的很少的相互作用,使用时间和内存效率的优化算法,全局收敛时,模型是可学习的。在动态设置中,我们表明,结构感知的动态分类个性化可以有遗憾,是一个数量级小于结构无知的方法。我们验证我们的理论结果经验。

英文摘要:

We study the problem of dynamic assortment personalization with large, heterogeneous populations and wide arrays of products, and demonstrate the importance of structural priors for effective, efficient large-scale personalization. Assortment personalization is the problem of choosing, for each individual (type), a best assortment of products, ads, or other offerings (items) so as to maximize revenue. This problem is central to revenue management in e-commerce and online advertising where both items and types can number in the millions. We formulate the dynamic assortment personalization problem as a discrete-contextual bandit with $m$ contexts (types) and exponentially many arms (assortments of the $n$ items). We assume that each type's preferences follow a simple parametric model with $n$ parameters. In all, there are $mn$ parameters, and existing literature suggests that order optimal regret scales as $mn$. However, the data required to estimate so many parameters is orders of magnitude larger than the data available in most revenue management applications; and the optimal regret under these models is unacceptably high. In this paper, we impose a natural structure on the problem -- a small latent dimension, or low rank. In the static setting, we show that this model can be efficiently learned from surprisingly few interactions, using a time- and memory-efficient optimization algorithm that converges globally whenever the model is learnable. In the dynamic setting, we show that structure-aware dynamic assortment personalization can have regret that is an order of magnitude smaller than structure-ignorant approaches. We validate our theoretical results empirically.

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。

↑